DETAILED ACTION
This is the first action regarding application number 17/846,007 filed 06/03/2026. Claims 1-2, 4-5, 11-12 and 14-15 were amended while claims 6-7 and 16-17 were cancelled. Claims 1-5, 8-15 and 18-20 have been examined and are pending.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 06/03/2026 has been entered.
Benefit
Domestic benefit of 08/20/2021 is acknowledged.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-5, 8-15 and 18-20 are rejected under 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph, as based on a disclosure which is not enabling. The disclosure does not enable one of ordinary skill in the art to practice the invention without wherein the expanded search space is characterized by a first range of network depths and a second range of network widths…partitioning the expanded search space further includes assigning each network space a sub-range of the first range and a sub-range of the second range…the network spaces including a given network space that is assigned a first sub-range of the first range and a second sub-range of the second range, which is/are critical or essential to the practice of the invention but not included in the claim(s). See In re Mayhew, 527 F.2d 1229, 188 USPQ 356 (CCPA 1976). Limitations state an expanded search space has a range of depths and widths, the expanded search space is partitioned to form network spaces with a sub-range of the depths and widths and then the underlined section states that each network space is assigned sub-range again, however it has already been assigned a sub-range. These limitations appear to contain either redundant or contradictory claim language as the network spaces have already been assigned a sub-range.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 1-5, 8-15 and 18-20 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 1 and 11 recite the limitation each network architecture. There is insufficient antecedent basis for this limitation in the claim. It is unclear if this refers to specifically to the plurality of network architecture, a specific network architecture, all architectures in all network spaces, or the set of architectures in a single network space. Examiner will interpret the limitation as wherein each of the plurality of network architectures.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 1-5, 8-15 and 18-20 rejected under 35 U.S.C. 101 because claims are directed towards an abstract idea(s) without significantly more.
Regarding Claim 1:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites partitioning an expanded search space into a plurality of…spaces with each…space including a plurality of…architectures, each…architecture having a same number of stages and each stage having a same…width wherein the expanded search space is characterized by a first range of…depths and a second range of…widths… and partitioning the expanded search space further includes assigning each…space a sub-range of the first range and a sub-range of the second range which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass defining subsets of a set using judgement to selecting disjoint ranges from a set while keeping characteristics similar between the ranges. See 2106.04.(a)(2).III.C.
The claim recites sampling respective…architectures in the…spaces which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass a user choosing or selecting a set from a list of sets(2106.04.(a)(2).III.C).
The claim recites the…spaces including a given…space that is assigned a first sub-range of the first range and a second sub-range of the second range, wherein the sampling further comprises: for each stage in the given…space, which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass defining subsets of a set using judgement to selecting disjoint ranges from a set of ranges. See 2106.04.(a)(2).III.C.
The claim recites sampling a respective number d from the first sub-range as a…depth for that stage, and sampling a respective number w from the second sub-range as a…width for that stage which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass a user choosing or selecting a set from a list of sets(2106.04.(a)(2).III.C).
The claim recites evaluating performance of the…spaces by evaluating the respective…architectures with respect to a multi-objective loss function, wherein the evaluated performance is indicated as a probability associated with each…space which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites identifying a subset of the … spaces that has highest probabilities which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass a user making an evaluation of multiple sets (2106.04.(a)(2).III.C). Alternatively, the BRI of the claims can be categorized as abstract idea using math(Mathematical Relationships (see MPEP 2106.04(a)(2)(I)(A))).
The claim recites selecting a target…space from the subset as output of the…space search wherein the target…space has an operation count that is closest to a predetermined target operation count has a…count that is closest to a…count constraint which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass a user making a choice and selecting a particular subset of set based on a count of number of operations performed (2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
Network/networks(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))).
to reduce computational costs of the hardware platform, wherein the target network space serves as a search space for subsequent neural architecture search(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
floating-point operation (FLOP)… FLOP(specifies linking the use of a judicial exception to a particular technological environment or field of use(see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
Additional elements (b) do not integrate the abstract idea into a practical application nor
do the additional limitation provide significantly more than the abstract idea because the
limitation amount to no more than mere instructions to apply the exception using a generic
computer component. Please see MPEP §2106.05(f). Specifically, the elements falls into
§2106.05(f)(1) as the claim recites only the idea of a solution or outcome i.e., the claim fails to
recite details of how a solution to a problem is accomplished. The recitation of claim limitations
that attempt to cover any solution to an identified problem with no restriction on how the result is
accomplished and no description of the mechanism for accomplishing the result, does not
integrate a judicial exception into a practical application or provide significantly more because
this type of recitation is equivalent to the words "apply it".
Additional elements (c) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely links the use of a judicial exception to a particular technological environment or field of use(see MPEP 2106.05(h)).
The additional element(s) (a) (b) and (c) in the claim do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding Claim 2:
The rejection of claim 1 is incorporated and further claim recites further additional
elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim does not contain elements that would warrant a Step 2A Prong 1 analysis.
Subject Matter Eligibility Analysis Step 2A Prong 2:
wherein each network architecture in the expanded search space includes a stem network to receive an input, a prediction network to generate an output, and a network body that includes the same number of stages(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) do not integrate the abstract idea into a practical application because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in the claim do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding Claim 3:
The rejection of claim 1 is incorporated and further claim recites further additional
elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:.
The claim recites wherein the multi-objective loss function includes a task-specific loss function and a model complexity function which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
The claim does not contain elements that would warrant a Step 2A Prong 2 analysis.
Subject Matter Eligibility Analysis Step 2B:
The claim does not include any additional element, when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding Claim 4:
The rejection of claim 3 is incorporated and further claim recites further additional
elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites wherein the model complexity function calculates complexity of a network architecture in terms of the FLOP count which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
The claim does not contain elements that would warrant a Step 2A Prong 2 analysis.
Subject Matter Eligibility Analysis Step 2B:
The claim does not include any additional element, when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding Claim 5:
The rejection of claim 3 is incorporated and further claim recites further additional
elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites wherein the model complexity function calculates a ratio of the FLOP count to the FLOP count constraint which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
The claim does not contain elements that would warrant a Step 2A Prong 2 analysis.
Subject Matter Eligibility Analysis Step 2B:
The claim does not include any additional element, when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding Claim 8:
The rejection of claim 1 is incorporated and further claim recites further additional
elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim does not contain elements that would warrant a Step 2A Prong 2 analysis.
Subject Matter Eligibility Analysis Step 2A Prong 2:
wherein each block is a residual block including two convolution sub-blocks(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) do not integrate the abstract idea into a practical application because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in the claim do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding Claim 9:
The rejection of claim 1 is incorporated and further claim recites further additional
elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites sampling the network architectures in each network space using at least a portion of the weights of the super network which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass a user selecting particular network architectures based on a weight preference. Please see 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
training a super network with a maximum network depth and a maximum network width to obtain weights (merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
The additional element(s) (a) in the claim do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding Claim 10:
The rejection of claim 1 is incorporated and further claim recites further additional
elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites wherein evaluating the performance further comprises optimizing a probability distribution over the network spaces which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass a user making changes and evaluating how the changes reflect the rest of the environment(2106.04.(a)(2).III.C) and Mathematical Relationships (see MPEP 2106.04(a)(2)(I)(A))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
The claim does not contain elements that would warrant a Step 2A Prong 2 analysis.
Subject Matter Eligibility Analysis Step 2B:
The claim does not include any additional element, when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding Claim 11:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites partitioning an expanded search space into a plurality of…spaces with each…space including a plurality of…architectures, each…architecture having a same number of stages and each stage having a same…width wherein the expanded search space is characterized by a first range of…depths and a second range of…widths… and partitioning the expanded search space further includes assigning each…space a sub-range of the first range and a sub-range of the second range which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass defining subsets of a set using judgement to selecting disjoint ranges from a set while keeping characteristics similar between the ranges. See 2106.04.(a)(2).III.C.
The claim recites sampling respective…architectures in the…spaces which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass a user choosing or selecting a set from a list of sets(2106.04.(a)(2).III.C).
The claim recites the…spaces including a given…space that is assigned a first sub-range of the first range and a second sub-range of the second range, wherein the sampling further comprises: for each stage in the given…space, which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass defining subsets of a set using judgement to selecting disjoint ranges from a set of ranges. See 2106.04.(a)(2).III.C.
The claim recites sampling a respective number d from the first sub-range as a…depth for that stage, and sampling a respective number w from the second sub-range as a…width for that stage which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass a user choosing or selecting a set from a list of sets(2106.04.(a)(2).III.C).
The claim recites evaluating performance of the…spaces by evaluating the respective…architectures with respect to a multi-objective loss function, wherein the evaluated performance is indicated as a probability associated with each…space which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites identifying a subset of the … spaces that has highest probabilities which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass a user making an evaluation of multiple sets (2106.04.(a)(2).III.C). Alternatively, the BRI of the claims can be categorized as abstract idea using math(Mathematical Relationships (see MPEP 2106.04(a)(2)(I)(A))).
The claim recites selecting a target…space from the subset as output of the…space search wherein the target…space has an operation count that is closest to a predetermined target operation count has a…count that is closest to a…count constraint which, under the broadest reasonable interpretation, covers performance of the limitation in the mind. The limitations encompass a user making a choice and selecting a particular subset of set based on a count of number of operations performed (2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
one or more processors; and memory to store instructions, when executed by the one or more processors, cause the system(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
Network/networks(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))).
to reduce computational costs of the hardware platform, wherein the target network space serves as a search space for subsequent neural architecture search(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
floating-point operation (FLOP)… FLOP(specifies linking the use of a judicial exception to a particular technological environment or field of use(see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
Additional elements (b) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
Additional elements (c) do not integrate the abstract idea into a practical application nor
do the additional limitation provide significantly more than the abstract idea because the
limitation amount to no more than mere instructions to apply the exception using a generic
computer component. Please see MPEP §2106.05(f). Specifically, the elements falls into
§2106.05(f)(1) as the claim recites only the idea of a solution or outcome i.e., the claim fails to
recite details of how a solution to a problem is accomplished. The recitation of claim limitations
that attempt to cover any solution to an identified problem with no restriction on how the result is
accomplished and no description of the mechanism for accomplishing the result, does not
integrate a judicial exception into a practical application or provide significantly more because
this type of recitation is equivalent to the words "apply it".
Additional elements (d) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely links the use of a judicial exception to a particular technological environment or field of use(see MPEP 2106.05(h)).
The additional element(s) (a) (b) (c) and (d) in the claim do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 12:
The rejection of claim 11 incorporated in claim 12. Claim 12 is rejected under the same rationale as set forth in the rejection of claim 2.
Regarding claim 13:
The rejection of claim 11 incorporated in claim 13. Claim 13 is rejected under the same rationale as set forth in the rejection of claim 3.
Regarding claim 14:
The rejection of claim 13 incorporated in claim 14. Claim 14 is rejected under the same rationale as set forth in the rejection of claim 4.
Regarding claim 15:
The rejection of claim 13 incorporated in claim 15. Claim 15 are rejected under the same rationale as set forth in the rejection of claim 5.
Regarding claim 18:
The rejection of claim 11 incorporated in claim 18. Claim 18 is rejected under the same rationale as set forth in the rejection of claim 8.
Regarding claim 19:
The rejection of claim 11 incorporated in claim 19. Claim 19 is rejected under the same rationale as set forth in the rejection of claim 9.
Regarding claim 20:
The rejection of claim 11 incorporated in claim 20. Claim 20 is rejected under the same rationale as set forth in the rejection of claim 10.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-5, 8-15 and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhao et al(“Few-shot Neural Architecture Search” henceforth known as Zhao) in view of Radosavovic et al(“Designing Network Design Spaces” henceforth known as Radosavovic1) in further view of Radosavovic et al(“On Network Design Spaces for Visual Recognition” henceforth known as Radosavovic2) with Fang et al.(“Densely Connected Search Space for More Flexible Neural Architecture Search”, henceforth known as Fang) and Luo et. al(“Semi-Supervised Neural Architecture Search”, henceforth known as Luo)
Regarding claim 1:
Zhao discloses partitioning an expanded search space into a plurality of network spaces with each network space including a plurality of network architectures(Zhao, Page 2, Col. 1, Paragraph 2, “we separate the entire search space Ω…into disjoint partitions”)…wherein the expanded search space is characterized by a first range of network depths and a second range of network widths, and partitioning the expanded search space further includes assigning each network space a sub-range of the first range and a sub-range of the second range(Zhao, Page 2, Col. 1, Paragraph 2, “we separate the entire search space Ω…into disjoint partitions” and Zhao, Page 1, Figure 1 shows 𝛀𝑨 = 𝛀𝑪 ∪ 𝛀D, where partitioning at least some widths and at least some depths in a range of widths of depths meets the language of the claim as the partitioned when joined form the complete search space and Figure 1 showing the entire search space being separated into separate and disjoint portions)
Zhao discloses sampling respective network architectures in the network spaces(Zhao, Page 4, Col. 2, Paragraph 5, “By starting with a few initial architectures, search-based algorithms sample the next architecture A from the search space based on previous sampled architectures and search algorithms until an architecture with satisfactory performance is found”), the network spaces including a given network space that is assigned a first sub-range of the first range and a second sub-range of the second range(Zhao, Page 2, Col. 1, Paragraph 2, “we separate the entire search space Ω…into disjoint partitions” and Zhao, Page 1, Figure 1 shows 𝛀𝑨 = 𝛀𝑪 ∪ 𝛀D, where partitioning at least some widths and at least some depths in a range of widths of depths meets the language of the claim as the partitioned when joined form the complete search space and Figure 1 showing the entire search space being separated into separate and disjoint portions)
Zhao discloses evaluating performance of the network spaces and selecting a target network space from the subset as output of the network space search(Zhao, Page 4, Col. 2, Paragraph 4, “we train these sub-supernets to converge and choose the sub-supernet SΩ with the lowest validation loss from all sub-supernets. Lastly, we pick the best architecture A∗ from the SΩ”)
Zhao does not disclose the following limitations:
each network architecture having a same number of stages and each stage having a same network width
wherein the sampling further comprises for each stage in the given network space, sampling a respective number d from the first sub-range as a network depth for that stage, and sampling a respective number w from the second sub-range as a network width for that stage
by evaluating the respective network architectures with respect to a multi-objective loss function, wherein the evaluated performance is indicated as a probability associated with each network space
identifying a subset of the network spaces that has highest probabilities
wherein the target network space as a floating-point operation (FLOP) count that is closest to a FLOP count constraint to reduce computational costs of the hardware platform, wherein the target network space serves as a search space for subsequent neural architecture search (NAS)
Radosavovic1 discloses each network architecture having a same number of stages and each stage having a same network width(Radosavovic1, Page 6, Col. 2, Paragraph 3, “We can convert the per-block wj to our per-stage format by simply counting the number of blocks with constant width, that is, each stage I has block width wi =w0·wim and number of blocks di” where, within any one stage, the blocks share a same stage width wi and Figure 7, where Figure 7 report increasing widths per stage, constant width per stage and decreasing width per stage )
References Zhao and Radosavovic1 are analogous art because they are from the same field of endeavor of using computer-implemented techniques for designing/selecting high-performing architecture from a space of possible network architectures.
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Zhao and Radosavovic1 before him or her, to modify network architecture of Zhao to include width pattern and structural rule of Radosavovic1 to simplify model designs for dimensionality and interpretability. The suggestion/motivation for doing so would have been Radosavovic1, Page 2, Col. 2, Paragraph 1, “The general strategy we adopt is to progressively design simplified versions of an initial, relatively unconstrained, design space while maintaining or improving its quality.” and Radosavovic1, Page 3, Col. 1, Paragraph 5, “Relative to the AnyNet design space, theRegNet design space is: (1) simplified both in terms of its dimension and type of network configurations it permits, (2) contains a higher concentration of top-performing models, and (3) is more amenable to analysis and interpretation.”
Zhao-Radosavovic1does not disclose the following limitations:
wherein the sampling further comprises for each stage in the given network space, sampling a respective number d from the first sub-range as a network depth for that stage, and sampling a respective number w from the second sub-range as a network width for that stage
by evaluating the respective network architectures with respect to a multi-objective loss function, wherein the evaluated performance is indicated as a probability associated with each network space
identifying a subset of the network spaces that has highest probabilities
wherein the target network space as a floating-point operation (FLOP)count that is closest to a FLOP count constraint to reduce computational costs of the hardware platform, wherein the target network space serves as a search space for subsequent neural architecture search (NAS)
Radosavovic2 discloses wherein the sampling further comprises for each stage in the given network space, sampling a respective number d from the first sub-range as a network depth for that stage, and sampling a respective number w from the second sub-range as a network width for that stage(Radosavovic2, Page 3, Col. 2, Table 2, “Independently for each of the three network stages i, we select the number of blocks di and the number of channels per block wi. Notation a, b, n means we sample from nvalues spaced about evenly (in log space) in the range a to b.” where the sampling n values in a range from a finite range corresponds )
References Zhao-Radosavovic1 and Radosavovic2 are analogous art because they are from the same field of endeavor of evaluating large spaces of candidate network architectures to identify to better model.
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Zhao-Radosavovic1 and Radosavovic2 before him or her, to modify the sampling of Zhao-Radosavovic1 to include the distributions of Radosavovic2 to optimize allow for more controlled comparisons of search spaces. The suggestion/motivation for doing so would have been Radosavovic2, Page 7, Col. 2, Paragraph 2, “This spreads the range of the complexity distributions for each design space, allowing for more controlled comparisons.”
Zhao-Radosavovic1-Radosavovic2 does not disclose the following limitations:
by evaluating the respective network architectures with respect to a multi-objective loss function, wherein the evaluated performance is indicated as a probability associated with each network space
identifying a subset of the network spaces that has highest probabilities
wherein the target network space as a floating-point operation (FLOP)count that is closest to a FLOP count constraint to reduce computational costs of the hardware platform, wherein the target network space serves as a search space for subsequent neural architecture search (NAS)
Fang discloses evaluating performance of the network spaces by evaluating the respective network architectures with respect to a multi-objective loss function(Page 5, Col. 2, Equation 8 and Paragraph 2, “We design a loss function with the cost-based regularization to achieve the multi-objective optimization”), wherein the evaluated performance is indicated as a probability associated with each network space(Fang, Page 7, Col. 2, Table 4, “Comparisons with other search spaces on ImageNet. SS:SearchSpace. MBV2:MobileNetV2” where the accuracy of each search space is considered an empirical proportion and thus a probability)
Fang discloses identifying a subset of the network spaces that has highest probabilities(Fang, Page 2, Col. 1, Paragraph 4, “The final block connection paths in the super network are derived based on the probability distribution” and Page 5, Col. 2, Paragraph 6, “At the network level, we use the Viterbi algorithm to derive the paths connecting the blocks with the highest total transition probability based on the output path probabilities”)
Fang discloses selecting a target network space from the subset as output of the network space search wherein the target network space as a floating-point operation (FLOP)count (Fang, Page 2, Col. 2, Paragraph 6, “Our proposed method designs a densely connected search space beyond conventional search constrains to generate the architecture with a better trade-off between accuracy and model cost” where the selecting of best path is based on trade-off of accuracy and model cost is considered selecting a target network space of the optimized network (See also Fang, Page 2, Col. 1, Paragraph 4, “To optimize the cost (FLOPs/latency) of the network, we design a chained estimation algorithm targeted at approximating the cost of the model during the search”))
References Zhao-Radosavovic1-Radosavovic2 and Fang are analogous art because they are from the same field of endeavor of making neural architecture search more flexible by changing the design space and searching blocks of widths/counts.
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Zhao-Radosavovic1-Radosavovic2 and Fang before him or her, to modify the final model selection of Zhao-Radosavovic1-Radosavovic2 to include the evaluation, identification and selection steps of Fang to optimize both the accuracy and cost. The suggestion/motivation for doing so would have been Fang, Page 5, Col. 1, Paragraph 3, “We propose to optimize both the accuracy and the cost (latency/FLOPs) of the model. To this end, the model cost needs to be estimated during the search.”.
Zhao-Radosavovic1-Radosavovic2-Fang does not disclose the following limitations:
that is closest to a FLOP count constraint to reduce computational costs of the hardware platform, wherein the target network space serves as a search space for subsequent neural architecture search (NAS)
Luo discloses that is closest to a FLOP count constraint to reduce computational costs of the hardware platform, wherein the target network space serves as a search space for subsequent neural architecture search (NAS)(Luo, Page 7, Col. 1, Paragraph 1, “SemiNAS achieves 23.5% top-1 test error rate on ImageNet under the mobile setting (FLOPS ≤ 600 Million)” wherein choosing the network architecture based on <= 600M FLOPS corresponds to selecting a target network space that has an operation count that is closest to a predetermining target operation count)
References Zhao-Radosavovic1-Radosavovic2-Fang and Luo are analogous art because they are from the same field of endeavor of using neural architecture search to optimize networks.
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Zhao-Radosavovic1-Radosavovic2-Fang and Luo before him or her, to modify the target selection of Zhao-Radosavovic1-Radosavovic2-Fang to include the target operation count of Luo to target specific categories of hardware such as practical mobile system. The suggestion/motivation for doing so would have been Luo, Page 2, Paragraph 4, “For image classification…we achieve 23.5% top-1 error rate on ImageNet under the mobile setting” where the mobile setting refers to having a target of <= 600M FLOPS aimed at testing on mobile categories of hardware.
Regarding claim 2:
The rejection of claim 1 with prior art Zhao-Radosavovic1-Radosavovic2-Fang-Luo
is incorporated and further:
Fang discloses wherein each network architecture in the expanded search space includes a stem network to receive an input(Fang, Figure 2 and Page 11, Col. 1, Algorithm 1, “input Block B0” where the explicit input block B0 is considered an input stem network that receives an input as a routing block receives an input), a prediction network to generate an output(Fang, Page 4, Col. 2, Paragraph 6, “We assume that the routing block Bi outputs the tensor bi and connects to m subsequent blocks” where basic layers make a routing block and a routing block output is considered a prediction network generating an output(See Also Fang, Page 11, Col. 1, Algorithm 1, “routing blocks {B1…,BN}”)),, and a network body that includes the same number of stages(Fang, Page 4, Col. 1, Paragraph 5,“We partition the entire network into several stages… each stage contains routing blocks with various widths” where the partitioning of the network into a super network into stages is considered a network body that includes the predetermined number of stages as the number of stages are determined by the search space design)
Regarding claim 3:
The rejection of claim 1 with prior art Zhao-Radosavovic1-Radosavovic2-Fang-Luo
is incorporated and further:
Fang discloses wherein the multi-objective loss function includes a task-specific loss function and a model complexity function(Fang, Page 5, Col. 2, Equation 8, where equation 8 balancing cost(latency/FLOPS) and accuracy is considered a multi-objective function)
Regarding claim 4:
The rejection of claim 3 with prior art Zhao-Radosavovic1-Radosavovic2-Fang-Luo
is incorporated and further:
Fang discloses wherein the model complexity function calculates complexity of a network architecture in terms of the FLOP count( Fang, Page 5, Col. 1, Equation’s 5-6 and Paragraph 3, “ We propose to optimize both the accuracy and the cost (latency/FLOPs) of the model” where optimizing both the accuracy and cost in terms of FLOPs is considered calculating complexity of a network architecture of the number of floating-point operations (FLOPs))
Regarding claim 8:
The rejection of claim 1 with prior art Zhao-Radosavovic1-Radosavovic2-Fang-Luo
is incorporated and further:
Fang discloses wherein each block is a residual block including two convolution sub-blocks(Fang, Page 11, Table 6, where the application of DenseNAS in the ResNet search space shows stage 2-5 having two convolution sub-blocks)
Regarding claim 9:
The rejection of claim 1 with prior art Zhao-Radosavovic1-Radosavovic2-Fang-Luo
is incorporated and further:
Fang discloses training a super network with a maximum network depth and a maximum network width to obtain weights(Fang, Page 11, Col. 2, Paragraph 1, “The super network includes all the possible architectures defined in the search space…When training the weights…” where including all possible architectures of a search space when training weights corresponds to training with a maximum network depth and width to train weights) and sampling the network architectures in each network space using at least a portion of the weights of the super network(Fang, Page 11, Col. 2, Paragraph 1, “When training the weights of operations, we sample one path of the candidate operations … in every basic layer” where sampling one path of each basic layer during training is considered sampling each network space using at least a portion of the weights of the super network as the sampling reuses a portion of the weights in the path (See Fang, Page 11, Col. 2, Paragraph 1, “The dropping-path strategy not only accelerates the search but also weakens the coupling effect between operation weights shared by different sub-architectures in the search space.”))
Regarding claim 10:
The rejection of claim 1 with prior art Zhao-Radosavovic1-Radosavovic2-Fang-Luo
is incorporated and further:
Fang discloses optimizing a probability distribution over the network spaces(Fang, Page 5, Col. 2, Equation 8, where Equation 8 showing the multi-objective optimization that balances accuracy and efficiency with these parameters balances the accuracy and efficiency is considered optimizing a probability distribution over the network as α(Eq. 1) is layer-level architecture that weighs candidate operations inside each basic lay via softmax and β(Eq. 3) is the transition probabilities that weight the paths between routing blacks via softmax are both probability distributions)
Regarding claim 11:
Zhao discloses one or more processors; and memory to store instructions, when executed by the one or more processor(“These experiments ran on 50 P100 GPUs” where using P100’s GPU’s corresponds to having one or more processor, memory and executing memory using a processor)
Zhao discloses partition an expanded search space into a plurality of network spaces with each network space including a plurality of network architectures(Zhao, Page 2, Col. 1, Paragraph 2, “we separate the entire search space Ω…into disjoint partitions”)…wherein the expanded search space is characterized by a first range of network depths and a second range of network widths, and partitioning the expanded search space further includes assigning each network space a sub-range of the first range and a sub-range of the second range(Zhao, Page 2, Col. 1, Paragraph 2, “we separate the entire search space Ω…into disjoint partitions” and Zhao, Page 1, Figure 1 shows 𝛀𝑨 = 𝛀𝑪 ∪ 𝛀D, where partitioning at least some widths and at least some depths in a range of widths of depths meets the language of the claim as the partitioned when joined form the complete search space and Figure 1 showing the entire search space being separated into separate and disjoint portions)
Zhao discloses sampling respective network architectures in the network spaces(Zhao, Page 4, Col. 2, Paragraph 5, “By starting with a few initial architectures, search-based algorithms sample the next architecture A from the search space based on previous sampled architectures and search algorithms until an architecture with satisfactory performance is found”), the network spaces including a given network space that is assigned a first sub-range of the first range and a second sub-range of the second range(Zhao, Page 2, Col. 1, Paragraph 2, “we separate the entire search space Ω…into disjoint partitions” and Zhao, Page 1, Figure 1 shows 𝛀𝑨 = 𝛀𝑪 ∪ 𝛀D, where partitioning at least some widths and at least some depths in a range of widths of depths meets the language of the claim as the partitioned when joined form the complete search space and Figure 1 showing the entire search space being separated into separate and disjoint portions)
Zhao discloses evaluating performance of the network spaces and selecting a target network space from the subset as output of the network space search(Zhao, Page 4, Col. 2, Paragraph 4, “we train these sub-supernets to converge and choose the sub-supernet SΩ with the lowest validation loss from all sub-supernets. Lastly, we pick the best architecture A∗ from the SΩ”)
Zhao does not disclose the following limitations:
each network architecture having a same number of stages and each stage having a same network width
wherein the sampling further comprises for each stage in the given network space, sampling a respective number d from the first sub-range as a network depth for that stage, and sampling a respective number w from the second sub-range as a network width for that stage
by evaluating the respective network architectures with respect to a multi-objective loss function, wherein the evaluated performance is indicated as a probability associated with each network space
identifying a subset of the network spaces that has highest probabilities
wherein the target network space as a floating-point operation (FLOP)count that is closest to a FLOP count constraint to reduce computational costs of the hardware platform, wherein the target network space serves as a search space for subsequent neural architecture search (NAS)
Radosavovic1 discloses each network architecture having a same number of stages and each stage having a same network width(Radosavovic1, Page 6, Col. 2, Paragraph 3, “We can convert the per-block wj to our per-stage format by simply counting the number of blocks with constant width, that is, each stage I has block width wi =w0·wim and number of blocks di” where, within any one stage, the blocks share a same stage width wi and Figure 7, where Figure 7 report increasing widths per stage, constant width per stage and decreasing width per stage )
References Zhao and Radosavovic1 are analogous art because they are from the same field of endeavor of using computer-implemented techniques for designing/selecting high-performing architecture from a space of possible network architectures.
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Zhao and Radosavovic1 before him or her, to modify network architecture of Zhao to include width pattern and structural rule of Radosavovic1 to simplify model designs for dimensionality and interpretability. The suggestion/motivation for doing so would have been Radosavovic1, Page 2, Col. 2, Paragraph 1, “The general strategy we adopt is to progressively design simplified versions of an initial, relatively unconstrained, design space while maintaining or improving its quality.” and Radosavovic1, Page 3, Col. 1, Paragraph 5, “Relative to the AnyNet design space, theRegNet design space is: (1) simplified both in terms of its dimension and type of network configurations it permits, (2) contains a higher concentration of top-performing models, and (3) is more amenable to analysis and interpretation.”
Zhao-Radosavovic1does not disclose the following limitations:
wherein the sampling further comprises for each stage in the given network space, sampling a respective number d from the first sub-range as a network depth for that stage, and sampling a respective number w from the second sub-range as a network width for that stage
by evaluating the respective network architectures with respect to a multi-objective loss function, wherein the evaluated performance is indicated as a probability associated with each network space
identifying a subset of the network spaces that has highest probabilities
wherein the target network space as a floating-point operation (FLOP)count that is closest to a FLOP count constraint to reduce computational costs of the hardware platform, wherein the target network space serves as a search space for subsequent neural architecture search (NAS)
Radosavovic2 discloses wherein the sampling further comprises for each stage in the given network space, sampling a respective number d from the first sub-range as a network depth for that stage, and sampling a respective number w from the second sub-range as a network width for that stage(Radosavovic2, Page 3, Col. 2, Table 2, “Independently for each of the three network stages i, we select the number of blocks di and the number of channels per block wi. Notation a, b, n means we sample from nvalues spaced about evenly (in log space) in the range a to b.” where the sampling n values in a range from a finite range corresponds )
References Zhao-Radosavovic1 and Radosavovic2 are analogous art because they are from the same field of endeavor of evaluating large spaces of candidate network architectures to identify to better model.
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Zhao-Radosavovic1 and Radosavovic2 before him or her, to modify the sampling of Zhao-Radosavovic1 to include the distributions of Radosavovic2 to optimize allow for more controlled comparisons of search spaces. The suggestion/motivation for doing so would have been Radosavovic2, Page 7, Col. 2, Paragraph 2, “This spreads the range of the complexity distributions for each design space, allowing for more controlled comparisons.”
Zhao-Radosavovic1-Radosavovic2 does not disclose the following limitations:
by evaluating the respective network architectures with respect to a multi-objective loss function, wherein the evaluated performance is indicated as a probability associated with each network space
identifying a subset of the network spaces that has highest probabilities
wherein the target network space as a floating-point operation (FLOP)count that is closest to a FLOP count constraint to reduce computational costs of the hardware platform, wherein the target network space serves as a search space for subsequent neural architecture search (NAS)
Fang discloses evaluating performance of the network spaces by evaluating the respective network architectures with respect to a multi-objective loss function(Page 5, Col. 2, Equation 8 and Paragraph 2, “We design a loss function with the cost-based regularization to achieve the multi-objective optimization”), wherein the evaluated performance is indicated as a probability associated with each network space(Fang, Page 7, Col. 2, Table 4, “Comparisons with other search spaces on ImageNet. SS:SearchSpace. MBV2:MobileNetV2” where the accuracy of each search space is considered an empirical proportion and thus a probability)
Fang discloses identifying a subset of the network spaces that has highest probabilities(Fang, Page 2, Col. 1, Paragraph 4, “The final block connection paths in the super network are derived based on the probability distribution” and Page 5, Col. 2, Paragraph 6, “At the network level, we use the Viterbi algorithm to derive the paths connecting the blocks with the highest total transition probability based on the output path probabilities”)
Fang discloses selecting a target network space from the subset as output of the network space search wherein the target network space as a floating-point operation (FLOP)count (Fang, Page 2, Col. 2, Paragraph 6, “Our proposed method designs a densely connected search space beyond conventional search constrains to generate the architecture with a better trade-off between accuracy and model cost” where the selecting of best path is based on trade-off of accuracy and model cost is considered selecting a target network space of the optimized network (See also Fang, Page 2, Col. 1, Paragraph 4, “To optimize the cost (FLOPs/latency) of the network, we design a chained estimation algorithm targeted at approximating the cost of the model during the search”))
References Zhao-Radosavovic1-Radosavovic2 and Fang are analogous art because they are from the same field of endeavor of making neural architecture search more flexible by changing the design space and searching blocks of widths/counts.
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Zhao-Radosavovic1-Radosavovic2 and Fang before him or her, to modify the final model selection of Zhao-Radosavovic1-Radosavovic2 to include the evaluation, identification and selection steps of Fang to optimize both the accuracy and cost. The suggestion/motivation for doing so would have been Fang, Page 5, Col. 1, Paragraph 3, “We propose to optimize both the accuracy and the cost (latency/FLOPs) of the model. To this end, the model cost needs to be estimated during the search.”.
Zhao-Radosavovic1-Radosavovic2-Fang does not disclose the following limitations:
that is closest to a FLOP count constraint to reduce computational costs of the hardware platform, wherein the target network space serves as a search space for subsequent neural architecture search (NAS)
constraint to reduce computational costs of the one or more processors
Luo discloses that is closest to a FLOP count constraint to reduce computational costs of the one or more processors, wherein the target network space serves as a search space for subsequent neural architecture search (NAS)(Luo, Page 7, Col. 1, Paragraph 1, “SemiNAS achieves 23.5% top-1 test error rate on ImageNet under the mobile setting (FLOPS ≤ 600 Million)” wherein choosing the network architecture based on <= 600M FLOPS corresponds to selecting a target network space that has an operation count that is closest to a predetermining target operation count)
References Zhao-Radosavovic1-Radosavovic2-Fang and Luo are analogous art because they are from the same field of endeavor of using neural architecture search to optimize networks.
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art, having the teachings of Zhao-Radosavovic1-Radosavovic2-Fang and Luo before him or her, to modify the target selection of Zhao-Radosavovic1-Radosavovic2-Fang to include the target operation count of Luo to target specific categories of hardware such as practical mobile system. The suggestion/motivation for doing so would have been Luo, Page 2, Paragraph 4, “For image classification…we achieve 23.5% top-1 error rate on ImageNet under the mobile setting” where the mobile setting refers to having a target of <= 600M FLOPS aimed at testing on mobile categories of hardware.
Regarding claim 12:
The rejection of claim 11 incorporated in claim 12. Claim 12 is rejected under the same rationale as set forth in the rejection of claim 2.
Regarding claim 13:
The rejection of claim 11 incorporated in claim 13. Claim 13 is rejected under the same rationale as set forth in the rejection of claim 3.
Regarding claim 14:
The rejection of claim 13 incorporated in claim 14. Claim 14 is rejected under the same rationale as set forth in the rejection of claim 4.
Regarding claim 18:
The rejection of claim 11 incorporated in claim 18. Claim 18 is rejected under the same rationale as set forth in the rejection of claim 8.
Regarding claim 19:
The rejection of claim 11 incorporated in claim 19. Claim 19 is rejected under the same rationale as set forth in the rejection of claim 9.
Regarding claim 20:
The rejection of claim 11 incorporated in claim 20. Claim 20 is rejected under the same rationale as set forth in the rejection of claim 10.
Regarding claim 5:
The rejection of claim 3 with prior art Zhao-Radosavovic1-Radosavovic2-Fang-Luo
is incorporated and further:
Luo discloses wherein the model complexity function calculates a ratio of the FLOP count to the FLOP count constraint(Luo, Page 6, Paragraph 4, “From the results in Table2, SemiNAS achieves 23.5% top-1 test error rate on ImageNet under the 600M FLOPS constraint” and with Luo, Page 7, Table 2, where each performances of different methods use a FLOPS measurement that is under the 600M FLOPS constraint and is considered a ratio of the FLOP count to the FLOP count constraint as SemiNAS in Table to uses 599 out of 600 FLOPS.)
Regarding claim 15:
The rejection of claim 13 incorporated in claim 15. Claim 15 are rejected under the same rationale as set forth in the rejection of claim 5.
Relevant Prior Art:
While not used in the rejection Examiner believes these are relevant arts that may also cover limitations in the claims:
Hong et al.(Network Space Search for Pareto-Efficient Spaces) – matching non-patent literature
Response to Arguments
Applicant's arguments filed 06/03/2026 have been fully considered but they are not persuasive. A breakdown of arguments can be found below.
112:
Examiner’s 112 rejection outlined in the prior action dated 03/03/2026 has been withdrawn as claims 7 and 17 that contained the deficiencies have been cancelled.
101:
Applicant appears to argue on Pages 6-7 that the claims integrate into a practical application as the claimed method produces a target network space selected based on its FLOP count being closest to hardware platform constraint which directly ties the output to the computational costs of the hardware platform. Further, Applicant cites to the specification and asserts the added steps of partitioning a search space into sub-spaces/sub-spaces, sampling network architecture with depth d/width w and evaluating with a multi-objective loss function are not mental/math/abstract concepts and cannot be performed in the human mind.
Examiner respectfully disagrees as the BRI of partitioning encompasses separating a set of information into sub-ranges as the language used is a “search space” and “expanded search space” without additional elements that positively link the claims to a technological improvement. Examiner does not find the amended language of specifying the partitioning being a sub-range of the expanded search space and sampling within the sub-range to positively recite limitations or additional elements that incorporate the partitioning into significantly more. Further, although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). Applicant appears to be interpreting a narrower claim as the current claims do not positively recite providing a technological improvement concerning automatic neural network design that results in a reduced computational cost.
103:
Applicant appears to argue on pages 8-9 that Fang in view of Luo does not disclose "each network architecture having a same number of stages and each stage having a same network width" and "for each stage in the given network space.... sampling a respective number w from the second sub-range as a network width for that stage" as recited in amended claim 1. Further, Applicant argues Fang does not discuss partitioning into stages and selection/output of network space as claimed.
Applicant’s arguments with respect to claim(s) have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. New prior arts, Zhao. Radosavovic1 and Radosavovic2 have been cited and mapped to the limitations outlined by applicant.
Applicant appears to argue on pages 9 that Luo’s constraint of 600M FLOPS is predetermined and not a selection criterion that identifies a network space closest to a FLOP count constraint among a plurality of candidate spaces as claimed.
Examiner respectfully disagrees as the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). Applicant appears to be interpreting a narrower claim as the current claims do not positively recite selection of a specific FLOP constraint based on candidate space and the closest language Examiner count find in the claims recites wherein the target network space has a floating-point operation (FLOP)count that is closest to a FLOP count constraint to reduce computational costs of the hardware platform, wherein the target network space serves as a search space for subsequent neural architecture search (NAS). Examiner does not believe this limitation only encompasses the claimed interpretation of a selection criterion that identifies a network space closest to a FLOP count constraint among a plurality of candidate spaces, but also encompasses a predetermined FLOP count as claims are silent on how the FLOP count is decided and merely asserted that the FLOP count is one that reduce computational costs of the hardware platform.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHARLES JEFFREY JONES JR whose telephone number is (703)756-1414. The examiner can normally be reached Monday - Friday 8:00 - 5:00 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Kakali Chaki can be reached at 571-272-3719. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/C.J.J./Examiner, Art Unit 2122
/KAKALI CHAKI/Supervisory Patent Examiner, Art Unit 2122
Prosecution Insights