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 .
DETAILED ACTION
This action is in response to the application filed 11 March 2026. Claims 1, 2, 4, 5, 7, 9, 10, 12, 13, 15, 17, 18, 20, 21, 23, 25, 28, and 29 are amended. Claims 1-32 are pending and have been examined.
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 11 March 2026 has been entered.
Response to Arguments
Applicant' s arguments, see pages 8-10, filed 23 February 2026, with respect to the rejections of Claims 1-32 under 35 U.S.C. 101 have been fully considered but they are not persuasive.
APPLICANT'S ARGUMENT: Applicant argues (page 9, continued paragraph) that "generation of a second neural network from a first neural network by inversion and reversal, updating parameters based on outputs produced by providing outputs of the second neural network as inputs to the first neural network, and generating a second dataset using the updated second neural network is not something that can practically be performed by the human mind. ... These are operations that are not practically performed as mental steps (with or without pen and paper). Accordingly, the recitations of the independent claims do not recite abstract ideas."
EXAMINER'S RESPONSE: Examiner respectfully disagrees. Amended Claim 1 recites steps of inverting layers of a neural network, generating a neural network from inverted layers, updating network parameters based on network output, generating a dataset, and performing inferences, which appear to be mental process steps that can be performed in the mind or with pen and paper since, at the claimed level of generality, the recited steps may merely involve a representation of the neural network.
The recited additional element of amended Claim 1, obtaining network output and providing the output as input to a neural network, appears to recite a step that merely applies general purpose computing machinery to perform the mental process step.
APPLICANT'S ARGUMENT: Applicant argues (page 9, paragraph 1) that "Each of the independent claims include recitations in relation to generating a second dataset comprising approximations of data in a first dataset, where the second dataset is usable to train a third neural network. Additionally, claims 1, 9, and 17 include recitations related to processors and/or circuitry to invert layers of the first neural network... Accordingly, the recitations of the independent claims demonstrate integration into a practical application."
Applicant argues (page 10, paragraph 1) that "each of claims 1, 9, 17, and 25 are directed to an improvement to technology, related to generating a dataset usable to train a third neural network to perform inferences corresponding to those performed by a first neural network."
Applicant argues (page 10, paragraph 2) that "Applicant respectfully submits that at least some of claims 2-8, 10-16, 18-24, and 26-32 include additional recitations that further establish their allowability under 35 U.S.C. § 101. For example ... generating transpose convolutional layers based on a convolutional layer of the first neural network ... generating inverted batch normalization layers based on a linear transformation of a batch normalization layer of the first neural network ... inserting or adding an activation layer ... a reversed computational flow ... generating the second training data by inputting at least one of a logit or data indicative of an encoded feature ... finetuning based on a layer consistency loss and a reconstruction loss."
EXAMINER'S RESPONSE: Examiner respectfully disagrees the amended claims recite eligible subject matter. As indicated, the claim does not recite additional elements that integrate the recited mental process steps into a practical application or provide significantly more. Where the claims recite the purported improvement, the improvement appears to be in the mental process itself rather than in a computer or computing technology.
The claim limitation "the second dataset being usable to train a third neural network" appears to recite an intended use of the generated dataset, which does not confer patentability. Examiner notes that while amended Claim 1 recites an intended use for the second dataset, the claim does not positively recite a step of training.
Applicant' s arguments, see pages 10-14, filed 23 February 2026, with respect to the rejections of Claims 1-32 under 35 U.S.C. 103 have been fully 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.
APPLICANT'S ARGUMENT: Applicant argues (page 11, paragraph 2) that "Brahimi describes a teacher/student architecture that includes a decoder network configured to reverse the teacher network's computation flow .... However, Brahimi does not disclose circuitry that inverts one or more layers of the first neural network and generates a second neural network comprising one or more neural network layers generated by reversing the inverted one or more layers of the first neural network."
Applicant argues (page 12, paragraph 1) that "Tobing 's cyclic VAE feedback is in a different context (Tobing, Fig. l; Eqs. (13)-(17)) and does not teach the claimed use of output of the second neural network as input to the first neural network to obtain output of the first neural network for updating the second neural network."
EXAMINER'S RESPONSE: Examiner notes that Applicant's arguments are moot. Amended Claim 1 is now rejected under 35 U.S.C. 103 in view of Brahimi in view of Pilzer. Pilzer is relied on to teach the feature of updating a second neural network based on output of the first neural network obtained from providing output of the second neural network as input to the first neural network.
APPLICANT'S ARGUMENT: Applicant argues (page 13, paragraph 1) that "Applicant respectfully submits that the claimed invention and Mardani Korani were, not later than March 8, 2021, the effective filing date of the claimed invention, owned by or subject to an obligation of assignment to the same person, NVIDIA Corporation."
EXAMINER'S RESPONSE: Examiner notes that Applicant's arguments are moot. Claims 8, 16, 24, and 32 are now rejected under 35 U.S.C. 103 in view of Brahimi in view of Pilzer in view of Johnson.
APPLICANT'S ARGUMENT: Applicant argues (page 13, paragraph 2) that "claim 2 recites that inversion is performed 'based, at least in part, on constructing one or more inverses ... using parameters stored in the first neural network.' Brahimi 's discussion that a decoder 'must be adapted to inverse the Teacher's layers' does not disclose constructing such inverses using parameters stored in the first neural network, and Tobing likewise does not disclose this recitation."
EXAMINER'S RESPONSE: Examiner notes that Applicant's arguments pertain to newly claimed matter. In the rejection of amended Claim 2 below, Brahimi is shown to teach using the first network's CONV Block1 layer to construct the second network's DECONV Block5 layer, based on the CONV layer's output tensor shape as retrieved from the CONV layer's model data. Under BRI in light of the specification, a network layer's retrieved output tensor shape teaches or reasonably suggests a parameter stored in the first network, as supported by the instant specification at [0120]: "code, such as graph code, loads weight or other parameter information into processor ALUs based on an architecture of a neural network to which such code corresponds."
Claim Objections
Claims 3, 11, 19, and 27 are objected to because of the following informalities: the phrase "at least one of an inverted fully-connected layer, and inverted convolutional layer, or an inverted batch normalization layer" appears to contain a typographic error "and inverted convolutional layer" (emphasis added). For the purposes of examination, the phrase has been interpreted to read "an inverted convolutional layer." Appropriate correction or clarification is required.
Claim Rejections - 35 USC § 112
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.
Claims 13, 21, and 29 are 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.
Claim 13 recites the limitation "the inverted batch normalization layer." There is insufficient antecedent basis for this limitation in the claim. Claim 13 depends on Claim 11, which recites "wherein the one or more neural network layers comprises at least one of an inverted fully-connected layer, and inverted convolutional layer, or an inverted batch normalization layer," and therefore recites a alternative of the invention that does not require a batch normalization layer. Claims 21 and 29 are rejected under a similar rationale.
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.
Claims 1-32 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding Claim 1
Step 1
Claim 1 recites one or more processors comprising: circuitry, and thus the claimed manufacture falls within a statutory category of invention.
Step 2A Prong 1
The claim recites invert one or more layers of a first neural network trained using a first dataset, which is a mental process. The claim recites generate a second neural network comprising one or more neural network layers generated by reversing the inverted one or more layers of the first neural network, which is a mental process. The claim recites update one or more parameters of the second neural network, based, at least in part, on output of the first neural network, which is a mental process. The claim recites generate, using the updated second neural network, a second dataset comprising approximations of data in the first dataset, which is a mental process. The claim recites to perform inferences corresponding to those performed by the first neural network, which is a mental process.
Thus, the claim recites an abstract idea.
Step 2A Prong 2, Step 2B
The additional element obtained from providing output of the second neural network as input to the first neural network invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it"). The additional element the second dataset being usable to train a third neural network invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 2
Step 1
Regarding Claim 2, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
The claim recites invert the one or more layers of the first neural network based, at least in part, on constructing one or more inverses of the one or more layers using parameters stored in the first neural network, which is a mathematical idea.
Thus, the claim recites an abstract idea.
Step 2A Prong 2, Step 2B
The claim recites the circuitry is to invert, which invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it").
The claim lacks additional elements integrating it into a practical application or providing significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 3
Step 1
Regarding Claim 3, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
The claim recites generate a second neural network comprising one or more neural network layers generated by reversing the inverted one or more layers of the first neural network (as recited in Claim 1), wherein the one or more neural network layers comprise at least one of an inverted fully-connected layer, and inverted convolutional layer, or an inverted batch normalization layer
Thus, the claim recites an abstract idea.
Step 2A Prong 2, Step 2B
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 4
Step 1
Regarding Claim 4, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
The claim recites wherein the circuitry is further to invert one or more convolutional layers of the first neural network ... by generating one or more transpose convolutional layers based, at least in part, on a convolutional layer of the first neural network, which is a mental process, so the claim recites a judicial exception.
Step 2A Prong 2, Step 2B
The claim recites a the first neural network being pre-trained neural network, which invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it").
The claim lacks additional elements integrating it into a practical application or providing significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 5
Step 1
Regarding Claim 5, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
The claim recites wherein the circuitry is further to invert one or more batch normalization layers the first neural network ... by generating one or more inverted batch normalization layers based, at least in part, on a linear transformation of the one or more batch normalization layers of the first neural network, which is a mental process, so the claim recites a judicial exception.
Step 2A Prong 2, Step 2B
The claim recites the first neural network being pre-trained neural network, which invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it").
The claim lacks additional elements integrating it into a practical application or providing significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 6
Step 1
Regarding Claim 6, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
The claim recites wherein the circuitry is further to insert an activation layer, which is a mental process.
Thus, the claim recites an abstract idea.
Step 2A Prong 2, Step 2B
The claim lacks additional elements integrating it into a practical application or providing significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 7
Step 1
Regarding Claim 7, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
The claim recites wherein the second neural network comprising the one or more neural network layers outputs a facsimile of an input to the first neural network, which is a mental process.
Thus, the claim recites an abstract idea.
Step 2A Prong 2, Step 2B
The claim recites the first neural network being pre-trained neural network, which invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 8
Step 1
Regarding Claim 8, the rejection of Claim 1 is incorporated.
Step 2A Prong 1
The claim recites fine-tune the one or more neural network layers based, at least in part, on a layer consistency loss and a reconstruction loss, which is a mathematical idea, so the claim recites an abstract idea.
Step 2A Prong 2, Step 2B
The claim recites the circuitry is ... to fine-tune, which invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it").
The claim lacks additional elements integrating it into a practical application or providing significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 9
Step 1
Claim 9 recites a system, comprising: one or more processors, and thus the claimed machine falls within a statutory category of invention.
Step 2A Prong 1
The claim recites invert one or more layers of a first neural network trained using a first dataset, which is a mental process. The claim recites generate a second neural network comprising one or more neural network layers generated by reversing the inverted one or more layers of the first neural network, which is a mental process. The claim recites update one or more parameters of the second neural network, based, at least in part, on output of the first neural network, which is a mental process. The claim recites generate, using the updated second neural network, a second dataset comprising approximations of data in the first dataset, which is a mental process. The claim recites to perform inferences corresponding to those performed by the first neural network, which is a mental process.
Thus, the claim recites an abstract idea.
Step 2A Prong 2, Step 2B
The additional element obtained from providing output of the second neural network as input to the first neural network invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it"). The additional element the second dataset being usable to train a third neural network invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Claims 10-16 incorporate substantively the limitations of Claims 2-8, respectively, in system form and are rejected under the same rationale.
Regarding Claim 17
Step 1
Claim 17 recites a non-transitory machine-readable medium having stored thereon a set of instructions, and thus the claimed machine falls within a statutory category of invention.
Step 2A Prong 1
The claim recites invert one or more layers of a first neural network trained using a first dataset, which is a mental process. The claim recites generate a second neural network comprising one or more neural network layers generated by reversing the inverted one or more layers of the first neural network, which is a mental process. The claim recites update one or more parameters of the second neural network, based, at least in part, on output of the first neural network, which is a mental process. The claim recites generate, using the updated second neural network, a second dataset comprising approximations of data in the first dataset, which is a mental process. The claim recites to perform inferences corresponding to those performed by the first neural network, which is a mental process.
Thus, the claim recites an abstract idea.
Step 2A Prong 2, Step 2B
The additional element performed by one or more processors, cause the one or more processors invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it"). The additional element obtained from providing output of the second neural network as input to the first neural network invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it"). The additional element the second dataset being usable to train a third neural network invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Claims 18-24 incorporate substantively the limitations of Claims 2-8, respectively, in non-transitory machine-readable medium form and are rejected under the same rationale.
Regarding Claim 25
Step 1
Claim 25 recites a method, and thus the claimed process falls within a statutory category of invention.
Step 2A Prong 1
The claim recites inverting one or more layers of a first neural network trained using a first training data, which is a mental process. The claim recites generating an inverted neural network comprising one or more neural network layers based, at least in part, on reversing the inverted one or more layers of the first neural network, which is a mental process. The claim recites updating one or more parameters of the inverted neural network, based, at least in part, on output of the first neural network, which is a mental process. The claim recites to generate a second training data comprising approximations of the first training data, which is a mental process.
Thus, the claim recites an abstract idea.
Step 2A Prong 2, Step 2B
The additional element obtained from providing output of the second neural network as input to the first neural network invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it"). The additional element using the updated inverted neural network invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it"). The additional element training a third neural network using the second training data invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it").
The claim lacks additional elements that integrate it into a practical application or provide significantly more, so it is directed to an abstract idea and is ineligible.
Regarding Claim 26
Step 1
Regarding Claim 26, the rejection of Claim 25 is incorporated.
Step 2A Prong 1
The claim recites generating an inverted neural network comprising one or more neural network layers based, at least in part, on reversing the inverted one or more layers of the first neural network (as recited in Claim 25), wherein the inverted neural network has a reversed computational flow with respect to the first neural network. which is a mental process.
Thus, the claim recites an abstract idea.
Step 2A Prong 2, Step 2B
The claim lacks additional elements integrating it into a practical application or providing significantly more, so it is directed to an abstract idea and is ineligible.
Claims 27-30 and 32 incorporate substantively the limitations of Claims 3-6 and 8, respectively, in method form and are rejected under the same rationale.
Regarding Claim 31
Step 1
Regarding Claim 31, the rejection of Claim 25 is incorporated.
Step 2A Prong 1
Claim 31 recites the abstract ideas recited by parent Claim 25.
Step 2A Prong 2, Step 2B
The additional element generating the second training data by inputting at least one of a logit or data indicative of an encoded feature to the inverted neural network invokes a computer or other machinery merely as a tool to perform an existing process (MPEP 2106.05(f), "apply it").
The claim lacks additional elements integrating it into a practical application or providing significantly more, so it is directed to an abstract idea and is ineligible.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
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.
Claims 1-3, 6, 7, 9-11, 14, 15, 17-19, 22, 23, 25-27, 30, and 31 are rejected under 35 U.S.C. 103 as being unpatentable over Brahimi, et al., "Deep interpretable architecture for plant diseases classification" (hereinafter "Brahimi") in view of Pilzer, et al., "Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation" (hereinafter "Pilzer").
Regarding Claim 1, Brahimi teaches:
One or more processors, comprising: circuitry (Brahimi, p. 4: "The code source of the proposed architecture is available at https://github.com/Tahedi1/Teacher_Student_Architecture" and source code file README.md, Usage: "Run the following code from the project folder: python visualization.py," where one or more processors comprising circuitry is inherent is executing Python code) to:
invert one or more layers of a first neural network (Brahimi, p. 2, Figure 1: Teacher/Student network architecture, depicting inversion of Teacher network blocks as corresponding Decoder network blocks, for example, convolutional layer CONV Block 1 (Teacher) and deconvolutional layer DECONV Block 5 (Decoder), and p. 3, 3 Proposed method: "Fig. 1 details the Teacher/Student architecture. For the sake of simplicity, VGG16 [12] architecture is used as Teacher and Student. ... To use another architecture, the decoder must be adapted to inverse the Teacher’s layers") trained using a first dataset (Brahimi, source code file teacher_student.py of the cited repository, lines 15-16, "#Teacher's graph" and "base_model1 = VGG16( ... weights='imagenet' ...)," indicating pre-training of the teacher model on ImageNet dataset);
generate a second neural network (Brahimi, p. 2, Fig. 1, where Brahimi's Decoder network corresponds to the instant second neural network, and the source code file Teacher_student.py of the cited repository defines the function "build_graph," which generates and returns a second neural network model implemented via the Keras library) comprising one or more neural network layers generated by reversing the inverted one or more layers of the first neural network (Brahimi, p. 2, Fig. 1, Decoder network layers DECONV Block 1 – DECONV Block5, which are depicted in reverse order of the first "Teacher" network with respect to the data flow depicted by the black arrows);
update one or more parameters of the second neural network, based, at least in part, on output of the first neural network (Brahimi, p. 2, Fig. 1, depicting the Decoder network receiving input YT as output from the Teacher network, and p. 2, 3 Proposed method: "The whole network (Teacher + Decoder + Student) is trained to minimize jointly the losses of the two classifiers (Teacher and Student)" and p. 7, 4.3.1 Heatmaps comparison: "the Grad-CAM visualizations miss some important regions highlighted by the proposed method. ... In the Teacher/Student architecture, this propagation is ensured by a trainable decoder which makes the visualizations more precise," where Brahimi's decoder corresponds to the instant second neural network) ... ; and
generate, using the updated second neural network, a second dataset comprising approximations of data in the first dataset, the second dataset being usable to train a third neural network (Brahimi, 3.4 Reconstructed image refinement: "The second convolution layer (green in Fig. 1) expands the tensor to three channels to use it as the Student’s input," where Brahimi's second Decoder network generates inputs for the third Student network, as depicted by p. 5, Fig. 3, "Visualization images of the Teacher/Student architecture" and p. 5, 4.2 Visualization results: "The visualizations depicted on Fig. 3 represent the reconstructed three channels images used as an input for the Student," where Brahimi's reconstructed corresponds to the instant approximations) to perform inferences corresponding to those performed by the first neural network (Brahimi, p. 2, "The whole network (Teacher + Decoder + Student) is trained to minimize jointly the losses of the two classifiers (Teacher and Student)," where the teacher and student inferences correspond as indicated by the loss functions (1), (2), and (3) for corresponding inputs).
Brahimi teaches updating parameters of the second neural network on output of the first neural network.
Brahimi does not explicitly teach update one or more parameters of the second neural network, based, at least in part, on output of the first neural network obtained from providing output of the second neural network as input to the first neural network.
However, Pilzer teaches:
update one or more parameters of the second neural network, based, at least in part, on output of the first neural network (Pilzer, p. 5, 3.4. Network Training and Knowledge Self-Distillation: "In this section, we detail the losses employed to train the proposed network in an end-to-end fashion. Reconstruction. First, we employ a reconstruction and structure similarity loss for each network. ... By summing the losses of the three networks
G
s
,
G
b
and
G
i
, we obtain:
L
r
e
c
0
... The total reconstruction loss is:
L
r
e
c
... Self-Distillation. Finally, we propose to introduce a knowledge distillation loss. ... The total training loss is given by:
L
t
o
t
=
L
r
e
c
+
λ
L
d
i
s
t
(10)
," where Pilzer's
G
b
and
G
i
correspond to the instant second and first networks, respectively) obtained from providing output of the second neural network as input to the first neural network (Pilzer, p. 3, Fig. 2, "The proposed approach is composed of two modules. ... In the second module, a generator network
G
b
predicts the left-to-right disparity map
d
r
in order to re-synthesize the right image. The model obtained in this way forms a cycle. The cycle inconsistency is used by a third network to predict the final disparity map," depicting inconsistency loss
I
r
being an output of second network
G
b
provided as input to first network
G
i
).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Brahimi regarding updating parameters of the second neural network on output of the first neural network with those of Pilzer regarding updating one or more parameters of the second neural network based on output of the first neural network obtained from providing output of the second neural network as input to the first neural network.
The motivation to do so would be to facilitate using information regarding network inconsistency during training in order to further refine network outputs of the student network (Pilzer, p. 2, 1. Introduction: "from the generated image, we propose to re-synthesize the input image by estimating the opposite disparity. The resulting network forms a cycle. Second, a third network exploits the cycle inconsistency between the original and the reconstructed input images in order to refine the estimated depth maps. Our intuition is that inconsistency maps provide rich information which can be further exploited, as they indicate where the first two networks fail to predict disparity pixels. Finally, we propose to use the principle of distillation in order to transfer knowledge from the whole network, seen as a teacher, to the student network").
Regarding Claim 9, Brahimi teaches:
a system, comprising: one or more processors (Brahimi, p. 4: "The code source of the proposed architecture is available at https://github.com/Tahedi1/Teacher_Student_Architecture" and source code file README.md, Usage: "Run the following code from the project folder: python visualization.py," where a system comprising a processor is inherent is executing Python code) to: perform those steps recited by Claim 1. Claim 9 is rejected under the same rationale as Claim 1.
Regarding Claim 17, Brahimi teaches:
a non-transitory machine-readable medium having stored thereon a set of instructions (Brahimi, p. 4, Experimental Results, where a machine-readable medium is inherent in collection of results using a workstation and source code, with "The code source of the proposed architecture is available at" given repository location), which if performed by one or more processors, cause the one or more processors (Brahimi, p. 4: "In this section, we present the results of training and validation of the proposed architecture. ... Training and validation are executed on a workstation containing Graphical Processing Unit GPU Nvidia GTX 1080") to at least: perform those steps recited by Claim 1. Claim 17 is rejected under the same rationale as Claim 1.
Regarding Claim 2, the rejection of Claim 1 is incorporated. The Brahimi/Pilzer combination teaches:
wherein the circuitry is to invert the one or more layers of the first neural network based, at least in part, on constructing one or more inverses of the one or more layers using parameters stored in the first neural network (Brahimi, source code file teacher_student.py of the cited repository, demonstrating use of the Teacher network CONV Block1 layer to construct the Decoder DECONV Block5 layer, at line 28, where "conv1" represents the CONV layer's output tensor shape (corresponding to a parameter stored in the Teacher network layer) being used to construct the DECONV layer at lines 57-59 by use in "merge11" then "conv11," where parameter is understood from the instant specification to represent layer data such as output tensor shape, as in [0120]: "code, such as graph code, loads weight or other parameter information into processor ALUs based on an architecture of a neural network to which such code corresponds").
Regarding Claim 3, the rejection of Claim 1 is incorporated. The Brahimi/Pilzer combination teaches:
wherein the one or more neural network layers comprise at least one of an inverted fully-connected layer, and inverted convolutional layer, or an inverted batch normalization layer (Brahimi, p. 2, Fig. 1, "Teacher/Student network architecture," which depicts Teacher convolution layer "CONV Block5 (14, 14, 512) (7, 7, 512)" as inverted by Decoder de-convolution layer "DECONV Block1 (14, 14, 512) (7, 7, 512)").
Claims 11 and 19 incorporate substantively the limitations of Claim 3 in system and non-transitory machine-readable medium forms, respectively, and are rejected under the same rationale.
Regarding Claim 6, the rejection of Claim 1 is incorporated. The Brahimi/Pilzer combination teaches:
wherein the circuitry is further to insert an activation layer (Brahimi, p. 2, Fig. 1: "Teacher/Student network architecture," Decoder layers "CONV layer + Sigmoid" and "CONV layer + RELU," inserted after the final DECONV layer, and p. 4, 3.4 Reconstructed image refinement: "The last decoder’s convolution layer uses sigmoid activation function to scale the values in the interval [0, 1]").
Claims 14 and 22 incorporate substantively the limitations of Claim 6 in system and non-transitory machine-readable medium forms, respectively, and are rejected under the same rationale.
Regarding Claim 7, the rejection of Claim 1 is incorporated. The Brahimi/Pilzer combination teaches:
wherein the second neural network comprising the one or more neural network layers outputs a facsimile of an input (Brahimi, Figure 3: Visualization images of the Teacher/Student architecture, which depicts pairs of inputs to the first Teacher network and outputs of the second Decoder network, where the images are segmented versions of the inputs, and p. 5, 4.2 Visualization results: "The visualizations depicted on Fig. 3 represent the reconstructed three channels images used as an input for the Student," where Brahimi's reconstructed images corresponds to the instant input facsimile) to the first neural network, the first neural network being a pre-trained neural network (Brahimi, source code file Teacher_student.py of the source repository, which uses a pre-trained VGG16 convolutional network as the first Teacher network, with pre-training weights indicated by the parameter weights='imagenet').
Claims 15 and 23 incorporate substantively the limitations of Claim 7 in system and non-transitory machine-readable medium forms, respectively, and are rejected under the same rationale.
Regarding Claim 10, Brahimi teaches:
wherein the first neural network is a pre-trained neural network (Brahimi, source code file Teacher_student.py of the source repository, which uses a pre-trained VGG16 convolutional network as the first Teacher network, with pre-training weights indicated by the parameter weights='imagenet').
Claim 18 incorporates substantively the limitations of Claim 10 in non-transitory machine-readable medium form and is rejected under the same rationale.
Regarding Claim 25, Brahimi teaches:
A method (Brahimi, p. 2, Proposed method: "We propose a classification and visualization generic architecture, named Teacher/Student architecture, based on learning transfer from a first classifier (Teacher) to a second one (Student)") comprising:
inverting one or more layers of a first neural network (Brahimi, p. 2, Figure 1: Teacher/Student network architecture, depicting inversion of Teacher network blocks as corresponding Decoder network blocks, for example, convolutional layer CONV Block 1 (Teacher) and deconvolutional layer DECONV Block 5 (Decoder), and p. 3, 3 Proposed method: "Fig. 1 details the Teacher/Student architecture. For the sake of simplicity, VGG16 [12] architecture is used as Teacher and Student. ... To use another architecture, the decoder must be adapted to inverse the Teacher’s layers") trained using a first training data (Brahimi, source code file teacher_student.py of the cited repository, lines 15-16, "#Teacher's graph" and "base_model1 = VGG16( ... weights='imagenet' ...)," indicating pre-training of the teacher model on ImageNet dataset);
generating an inverted neural network (Brahimi, p. 2, Fig. 1, where Brahimi's Decoder network corresponds to the instant second neural network, and the source code file Teacher_student.py of the cited repository defines the function "build_graph," which generates and returns a second neural network model implemented via the Keras library) comprising one or more neural network layers based, at least in part, on reversing the inverted one or more layers of the first neural network (Brahimi, p. 2, Fig. 1, Decoder network layers DECONV Block 1 – DECONV Block5, which are depicted in reverse order of the first "Teacher" network with respect to the data flow depicted by the black arrows);
updating one or more parameters of the inverted neural network, based, at least in part, on output of the first neural network (Brahimi, p. 2, Fig. 1, depicting the Decoder network receiving input YT as output from the Teacher network, and p. 2, 3 Proposed method: "The whole network (Teacher + Decoder + Student) is trained to minimize jointly the losses of the two classifiers (Teacher and Student)" and p. 7, 4.3.1 Heatmaps comparison: "the Grad-CAM visualizations miss some important regions highlighted by the proposed method. ... In the Teacher/Student architecture, this propagation is ensured by a trainable decoder which makes the visualizations more precise," where Brahimi's decoder corresponds to the instant second neural network) ...; and
using the updated inverted neural network to generate a second training data comprising approximations of the first training data (Brahimi, 3.4 Reconstructed image refinement: "The second convolution layer (green in Fig. 1) expands the tensor to three channels to use it as the Student’s input," where Brahimi's second Decoder network generates inputs for the third Student network, as depicted by p. 5, Fig. 3, "Visualization images of the Teacher/Student architecture" and p. 5, 4.2 Visualization results: "The visualizations depicted on Fig. 3 represent the reconstructed three channels images used as an input for the Student"); and
training a third neural network using the second training data (Brahimi, p. 4, 4.1 Classification results: "At the beginning of training, the Teacher is more accurate than the student. This may be explained by the dependency of the Student on the representation constructed by the Teacher. However, the loss and the accuracy of the Teacher and the Student converge at the end of the training because the communicated representation becomes stable," where the Student is trained on second data produced by the Decoder from Teacher network output, as in p. 2, 3 Proposed method: "The whole network (Teacher + Decoder + Student) is trained to minimize jointly the losses of the two classifiers (Teacher and Student)," where the teacher and student inferences correspond as indicated by the loss functions (1), (2), and (3) for corresponding inputs).").
Brahimi teaches updating parameters of the second neural network on output of the first neural network.
Brahimi does not explicitly teach update one or more parameters of the second neural network, based, at least in part, on output of the first neural network obtained from providing output of the second neural network as input to the first neural network.
However, Pilzer teaches:
updating one or more parameters of the inverted neural network, based, at least in part, on output of the first neural network (Pilzer, p. 5, 3.4. Network Training and Knowledge Self-Distillation: "In this section, we detail the losses employed to train the proposed network in an end-to-end fashion. Reconstruction. First, we employ a reconstruction and structure similarity loss for each network. ... By summing the losses of the three networks
G
s
,
G
b
and
G
i
, we obtain:
L
r
e
c
0
... The total reconstruction loss is:
L
r
e
c
... Self-Distillation. Finally, we propose to introduce a knowledge distillation loss. ... The total training loss is given by:
L
t
o
t
=
L
r
e
c
+
λ
L
d
i
s
t
(10)
," where Pilzer's
G
b
and
G
i
correspond to the instant second and first networks, respectively) obtained from providing output of the inverted neural network as input to the first neural network (Pilzer, p. 3, Fig. 2, "The proposed approach is composed of two modules. ... In the second module, a generator network
G
b
predicts the left-to-right disparity map
d
r
in order to re-synthesize the right image. The model obtained in this way forms a cycle. The cycle inconsistency is used by a third network to predict the final disparity map," depicting inconsistency loss
I
r
being an output of second network
G
b
provided as input to first network
G
i
).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of Brahimi regarding updating parameters of the second neural network on output of the first neural network with those of Pilzer regarding updating one or more parameters of the second neural network based on output of the first neural network obtained from providing output of the second neural network as input to the first neural network.
The motivation to do so would be to facilitate using information regarding network inconsistency during training in order to further refine network outputs of the student network (Pilzer, p. 2, 1. Introduction: "from the generated image, we propose to re-synthesize the input image by estimating the opposite disparity. The resulting network forms a cycle. Second, a third network exploits the cycle inconsistency between the original and the reconstructed input images in order to refine the estimated depth maps. Our intuition is that inconsistency maps provide rich information which can be further exploited, as they indicate where the first two networks fail to predict disparity pixels. Finally, we propose to use the principle of distillation in order to transfer knowledge from the whole network, seen as a teacher, to the student network").
Regarding Claim 26, the rejection of Claim 25 is incorporated. The Brahimi/Pilzer combination teaches:
wherein the inverted neural network has a reversed computational flow with respect to the first neural network (Brahimi, p. 2, Fig. 1, which depicts the inverted Decoder network consuming output from the Teacher network and producing output corresponding to the input of the first Teacher network).
Regarding Claim 27, the rejection of Claim 25 is incorporated. The Brahimi/Pilzer combination teaches:
wherein the inverted neural network comprises at least one of an inverted fully-connected layer, and inverted convolutional layer, or an inverted batch normalization layer (Brahimi, p. 2, Fig. 1, "Teacher/Student network architecture," which depicts Teacher convolution layer "CONV Block5 (14, 14, 512) (7, 7, 512)" as inverted by Decoder de-convolution layer "DECONV Block1 (14, 14, 512) (7, 7, 512)").
Regarding Claim 30, the rejection of Claim 25 is incorporated. The Brahimi/Pilzer combination teaches:
further comprising adding an activation layer to the inverted neural network (Brahimi, p. 2, Fig. 1: "Teacher/Student network architecture," Decoder layers "CONV layer + Sigmoid" and "CONV layer + RELU," inserted after the final DECONV layer, and p. 4, 3.4 Reconstructed image refinement: "The last decoder’s convolution layer uses sigmoid activation function to scale the values in the interval [0, 1]").
Regarding Claim 31, the rejection of Claim 25 is incorporated. The Brahimi/Pilzer combination teaches:
generating the second training data by inputting at least one of a logit or data indicative of an encoded feature to the inverted neural network (Brahimi, p. 2, Fig. 1: "Teacher/Student network architecture" with p. 2, 3 Proposed method: "The decoder consumes the Teacher latent representations to reconstruct an image with the same dimension of the input image," where Brahimi's latent representations corresponds to the instant encoded feature data, as in p. 3, 3 Proposed method: "The Teacher/Student network is designed to reconstruct an image containing the discriminant features formed by the Teacher to help the Student training").
Claims 4, 12, 20, and 28 are rejected under 35 U.S.C. 103 as being unpatentable over Brahimi, et al., "Deep interpretable architecture for plant diseases classification" (hereinafter "Brahimi") in view of Pilzer, et al., "Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation" (hereinafter "Pilzer") in view of Iglovikov, et al. "Ternausnet: U-net with vgg11 encoder pre-trained on imagenet for image segmentation" (hereinafter "Iglovikov").
Regarding Claim 4, the rejection of Claim 1 is incorporated.
The Brahimi/Pilzer combination teaches:
wherein the circuitry is ... to invert one or more convolutional layers of the first neural network ... by generating one or more ... convolutional layers based, at least in part, on a convolutional layer of the first neural network (Brahimi, p. 2, Figure 1: Teacher/Student network architecture, depicting inversion of Teacher network blocks as corresponding Decoder network blocks, for example, convolutional layer CONV Block 1 (Teacher) and deconvolutional layer DECONV Block 5 (Decoder), and p. 3, 3 Proposed method: "Fig. 1 details the Teacher/Student architecture. For the sake of simplicity, VGG16 [12] architecture is used as Teacher and Student. ... To use another architecture, the decoder must be adapted to inverse the Teacher’s layers") ... the first neural network being a pre-trained neural network (Brahimi, source code file teacher_student.py of the cited repository, lines 15-16, "#Teacher's graph" and "base_model1 = VGG16( ... weights='imagenet' ...)," indicating pre-training of the teacher model on ImageNet dataset).
The Brahimi/Pilzer combination does not explicitly teach generating one or more transpose convolutional layers based, at least in part, on a convolutional layer.
However, Iglovikov teaches:
generating one or more transpose convolutional layers based, at least in part, on a convolutional layer of the first neural network (Iglovikov, p. 2, Fig. 1, 3x3 ConvTranspose2d(stride=2)+ReLU, where the skip-connection arrows connect the transpose layers to their corresponding convolutional layers in the encoder, and p. 2, II. Network Architecture: "To construct the decoder we use transposed convolutions layers that doubles the size of a feature map while reducing the number of channels by half. ... The resultant feature map is treated by convolution operation to keep the number of channels the same as in a symmetric encoder term. This upsampling procedure is repeated 5 times to pair up with 5 max poolings, as shown in Fig. 1").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the Brahimi/Pilzer combination regarding generation of a transposed convolutional layer for an inverted neural network from an untrained neural network with those of Iglovikov regarding generating one or more transpose convolutional layers based on a convolutional layer.
The motivation to do so would be to facilitate training models for segmentation tasks under circumstances where there are limited amounts of data (Iglovikov, p. 1, II. Network Architecture: "Every step in the expansive path consists of an upsampling of the feature map followed by a convolution. Hence, the expansive branch increases the resolution of the output. In order to localize, upsampled features, the expansive path combines them with high-resolution features from the contracting path via skip-connections [4]. The output of the model is a pixel-by-pixel mask that shows the class of each pixel. This architecture proved itself very useful for segmentation problems with limited amounts of data").
Claims 12, 20, and 28 incorporate substantively the limitations of Claim 4 in system, non-transitory machine-readable medium, and method forms, respectively, and are rejected under the same rationale.
Claims 5, 13, 21, and 29 are rejected under 35 U.S.C. 103 as being unpatentable over Brahimi, et al., "Deep interpretable architecture for plant diseases classification" (hereinafter "Brahimi") in view of Pilzer, et al., "Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation" (hereinafter "Pilzer") in view of Yamaguchi, et al. (US Patent Publication US 2021/0327456 A1, hereinafter "Yamaguchi").
Regarding Claim 5, the rejection of Claim 1 is incorporated. The Brahimi/Pilzer combination teaches:
invert one or more ... layers of of the first neural network ... by generating one or more inverted ... layers based, at least in part, on a ... transformation of the one or more ... layers (Brahimi, p. 2, Fig. 1, Decoder network layers DECONV Block 1 – DECONV Block5, which are depicted in reverse order of the first "Teacher" network with respect to the data flow depicted by the black arrows, and where each of the Decoder layers has input and output tensor dimensions that are inverted from those of the corresponding Teacher layers) ... the first neural network being a pre-trained neural network (Brahimi, source code file Teacher_student.py of the source repository, which uses a pre-trained VGG16 convolutional network as the first Teacher network, with pre-training weights indicated by the parameter weights='imagenet').
The Brahimi/Pilzer combination does not explicitly teach invert one or more batch normalization layers of a ... neural network by generating one or more inverted batch normalization layers based, at least in part, on a linear transformation of the one or more batch normalization layers of the pre-trained neural network.
However, Yamaguchi teaches invert one or more batch normalization layers of ... a ... neural network (Yamaguchi, Fig. 21, where the corresponding adaptive batch normalization layers designated "AdaBN" are indicated to be inverse layers, e.g.,
f
4
-
1
j
_
0
and
f
4
j
_
1
, as in [0089]: "adaptive batch normalization is introduced to Normalizing Flow. Specifically, at least one inverse transformation
f
i
-
1
z
of K transformations
{
f
i
z
}
i
=
1
K
to be used in Normalizing Flow is adaptive batch normalization"), by generating one or more inverted batch normalization layers based, at least in part, on a linear transformation of the one or more batch normalization layers of the ... neural network (Yamaguchi, [0213]: "AdaFlow is a method in which adaptive batch normalization is introduced into Normalizing Flow. ... Note that, in calculation of adaptive batch normalization, scale transformation and shift transformation, that is, calculation in the expression (24d) may be omitted. In other words, it is also possible to express that the inverse transformation
f
i
_
0
-
1
z
is adaptive batch normalization in which
γ
=
1
and
β
=
0
," where Yamaguchi's equation 24d expresses the normalized output of a batch normalization layer).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the Brahimi/Pilzer combination regarding inversion of a convolutional layer from a pre-trained encoder with those of Yamaguchi regarding inverting one or more batch normalization layers of a neural network by generating one or more inverted batch normalization layers based on a linear transformation of the one or more batch normalization layers.
The motivation to do so would be to enable the pre-trained encoder and the trained decoder to accommodate a broader distribution of inputs without decreasing accuracy, thus increasing applicability of the model (Yamaguchi, [0089]: "to enable the second probability distribution to be adaptively learned from a small amount of adaptive learning data with a small calculation cost, adaptive batch normalization is introduced to Normalizing Flow" and [0211]: "Domain adaptation is a technique of adjusting a learned model so that, in a case where distribution of learning data to be used for model learning is different from distribution of test data which is a target of processing using the learned model, accuracy of the processing using the learned model does not degrade due to a difference between the distribution" and [0212]: "While there are various methods for domain adaptation which can be combined with a deep neural network (DNN), here, adaptive batch normalization will be described").
Claims 13, 21, and 29 incorporate substantively the limitations of Claim 5 in system, non-transitory machine-readable medium, and method forms, respectively, and are rejected under the same rationale.
Claims 8, 16, 24, and 32 are rejected under 35 U.S.C. 103 as being unpatentable over Brahimi, et al., "Deep interpretable architecture for plant diseases classification" (hereinafter "Brahimi") in view of Pilzer, et al., "Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation" (hereinafter "Pilzer") in further view of Johnson, et al., "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" (hereinafter "Johnson").
Regarding Claim 8, the rejection of Claim 1 is incorporated. The Brahimi/Pilzer combination teaches:
wherein the circuitry is further to fine-tune the one or more neural network layers based, at least in part, on a ... loss (Brahimi, p. 3, 3 Proposed method: "The difference between the usual denoising autoencoder and this architecture lies in the loss function design. The denoising autoencoder minimizes a reconstruction loss while this architecture minimizes the classification loss of two classifiers," where Brahimi's minimizing a classification loss corresponds to the instant fine-tune based on a loss).
The Brahimi/Pilzer combination may not explicitly teach fine-tune the one or more neural network layers based, at least in part, on a layer consistency loss and a reconstruction loss.
However, Johnson teaches:
fine-tune the one or more neural network layers (Johnson, p. 2, 1 Introduction: "We train feed- forward transformation networks for image transformation tasks, but rather than using per-pixel loss functions depending only on low-level pixel information, we train our networks using perceptual loss functions that depend on high-level features from a pretrained loss network") based, at least in part, on a layer consistency loss and a reconstruction loss (Johnson, p. 5, 3 Method: "The loss network
ϕ
is used to define a feature reconstruction loss
l
f
e
a
t
ϕ
and a style reconstruction loss
l
s
t
y
l
e
ϕ
that measure differences in content and style between images. For each input image
x
we have a content target
y
c
and a style target
y
s
. For style transfer, the content target
y
c
is the input image
x
and the output image
y
^
should combine the content of
x
=
y
c
with the style of
y
s
" where Johnson's feature and style reconstruction losses correspond to the instant layer consistency and reconstruction losses, respectively, where the instant layer consistency loss of the instant specification at [0094]: "if inverted input X' is perceptually close to X, then layer consistency loss 506 between them should be small," is taught by Johnson at, p. 7, 3.2 Perceptual Loss Functions, Feature Reconstruction Loss: "Using a feature reconstruction loss for training our image transformation networks encourages the output image
y
^
to be perceptually similar to the target image
y
, but does not force them to match exactly").
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings of the Brahimi/Pilzer combination regarding fine-tuning an autoencoder based on classification loss with those of Johnson regarding fine-tuning the one or more neural network layers based on a layer consistency loss and a reconstruction loss.
The motivation to do so would be
to facilitate training networks capable of performing style transfer with qualitative visual results and runtime efficiency (Johnson, p. 1, Abstract: "We show results on image style transfer, where a feed-forward network is trained to solve the optimization problem proposed by Gatys et al in real-time. Compared to the optimization-based method, our network gives similar qualitative results but is three orders of magnitude faster. We also experiment with single-image super-resolution, where replacing a per-pixel loss with a perceptual loss gives visually pleasing results").
Claims 16, 24, and 32 incorporate substantively the limitations of Claim 8 in system, non-transitory machine-readable medium, and method forms, respectively, and are rejected under the same rationale.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Wang, et al., "adVAE: a Self-adversarial Variational Autoencoder with Gaussian Anomaly Prior Knowledge for Anomaly Detection," teach a method of anomaly detection using a self-adversarial regularization mechanism that adds discrimination training objectives to the encoder and the generator through adversarial training to prevent the autoencoder from overfitting the given normal data.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ROBERT N DAY whose telephone number is (703)756-1519. The examiner can normally be reached M-F 9-5.
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.
/R.N.D./Examiner, Art Unit 2122
/KAKALI CHAKI/Supervisory Patent Examiner, Art Unit 2122
Prosecution Insights