DETAILED ACTION
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 .
This office action is in response to the claimed amendment filed on June 11, 2026, in which claims 1-18 were canceled and claims 19-35 are presented for further examination.
Response to Arguments
Applicant’s arguments filed on June 11, 2026, with respect to claims 19-35 have been fully considered and are persuasive. The 35 USC 102 rejection set forth in the last office action have been withdrawn. However, Applicant's arguments with respect to the 35 USC 101 rejection have been fully considered but they are not persuasive.
Remark
Applicant asserted that “applying the domain knowledge” is neither nominally nor tangentially related to the invention claimed here because the specification links this feature to the accomplishment of a technological improvement in the field of artificial intelligence, because:
[0013] With the guidance of the domain knowledge, the generated modularized networks may provide structures that may represent human-interpretable reasoning process precisely, which may lead to improved performance;
[0027] Domain knowledge may provide guidance in a generation of a reasonable modularized network, as it may generally involve an optimization problem with a mixture of continuous and discrete variables in the generation. With the guidance of the domain knowledge, the generated modularized networks may provide structures that may represent human-interpretable reasoning process precisely, which may lead to improved performance;
[0034] In some aspects of the present disclosure, the modularized networks with respective structures shown in FIG. 3A and FIG. 3B may be appropriate for extracting different rules contained within different sets of inputs. In an aspect of the present disclosure, through training a dataset comprising sets of inputs and sets of outputs corresponding to respective sets of inputs, the network 200 or 700 may learn associations between the sets of inputs and corresponding structures that may be used to map to the respective correct outputs. For instance, a posterior distribution of structures of modularized networks may be learned by the PGM 210 and may be used for inferring a structure of a modularized network for an arbitrary set of inputs. In another aspect of the present disclosure, domain knowledge may be applied in generation of structures. For instance, domain knowledge may be applied on the posterior distribution of structures of modularized networks learned by the PGM 210 through the dataset as one or more posterior regularization constraints. With the guidance of the domain knowledge, the regularized distribution of structures of modularized networks may be used to generate a precise and interpretable structure for a set of inputs that may represent hidden rules among the set of inputs; and
[0040] With the guidance of the domain knowledge, the method 400 may be utilized to generate precise and interpretable structures for different sets of inputs, as the generated structures may capture hidden rules among the sets of inputs.
After further reviewed Applicant’s arguments in lieu of the cited portions of the original US Patent Publication, it is conceivable that the limitation “applying domain knowledge” is not directed to an improvement. The specification clearly states that “domain knowledge”: ([0013], may lead to improved performance; ([0027], may lead to improved performance); ([0034], may represent hidden rules among the set of inputs); and ([0040], may capture hidden rules among the sets of inputs). Applicant should duly note that the term “may” is generally construed as permissive or discretionary, not as a statement of fact, obligation or requirement. Therefore, the statement that the “domain knowledge may lead to improve performance” is not eligible for patenting under 35 USC 101 because it is not provided a specific, technological solution that improves the functioning of a computer or a technical field. It is also not integrated into a practical application with concrete benefits. Even if all the details contained in the specification were imported into the claims, the result would still not be a concrete implementation of the abstract idea.
The claim is viewed as a whole not directed to a solution of a “technological problem,” nor is it directed to an improvement in computer or network functionality and the additional claim elements do not provide meaningful limitations to transform the abstract idea into a practical application of the abstract idea or that the ordered combination amounts to significantly more than the abstract idea itself. Instead, the claimed element claims the abstract idea through the use of conventional devices, without offering any technological means of effecting that concept.
The recited “applying domain knowledge as one or more posterior regularization constraints on the determined posterior distribution” amounts to nothing more than an instruction to apply the abstract idea using a generic computer and does not render an abstract idea eligible.
The use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not integrate a judicial exception into a practical application or provide significantly more. See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); TLI Communications LLC v. AV Auto, LLC, 823 F.3d 607, 613, 118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit).
Similarly, "claiming the improved speed or efficiency inherent with applying the abstract idea on a computer" does not integrate a judicial exception into a practical application or provide an inventive concept. Intellectual Ventures I LLC v. Capital One Bank (USA), 792 F.3d 1363, 1367, 115 USPQ2d 1636, 1639 (Fed. Cir. 2015). In contrast, a claim that purports to improve computer capabilities or to improve an existing technology may integrate a judicial exception into a practical application or provide significantly more. McRO, Inc. v. Bandai Namco Games Am. Inc., 837 F.3d 1299, 1314-15, 120 USPQ2d 1091, 1101-02 (Fed. Cir. 2016); Enfish, LLC v. Microsoft Corp., 822 F.3d 1327, 1335-36, 118 USPQ2d 1684, 1688-89 (Fed. Cir. 2016) Therefore implementing an abstract idea on such a generic computer does not integrate the abstract idea into a practical application
In the contrary, the claims in Ex-parte Desjardins are directed to using an application plugin to transform a dataset of an application-internal module configured to communicate with another application-internal module from a source schema to a target schema that makes the dataset accessible to an additional application. The transformation allows external applications to access the data without exposing the source data to the external applications (see, e.g., claims 4, 5). Therefore, the Appeals Review Panel determined the specification (Desjardins, p. 9) described improvements to the functioning of a computer and the improvements were reflected in the claims. Moreover, claims 1, 13, and 20 (Desjardins) recite features that reflect improvements to the functioning of a computer and/or to another technology. The claims recite improvements to how a computer communicates between applications. In particular, the claims recite a process performed using an application plugin that transforms a dataset that is used internally in an application to make that dataset available for ingestion to an external application that did not previously have access to the dataset, which reflects improvements to data structures in the computer.
Applicant should also note, while the claims in Desjardins were directed to training a machine learning model, the principles underlying the decision in Desjardins are not limited to machine learning models; and the Federal Circuit’s decision in Enfish, which is not directed to a machine learning model. Citing Enfish, the Appeals Review Panel emphasized that much of the advancement made in computer technology consists of improvements to software that, by their very nature, may not be defined by particular physical features but rather by logical structures and processes.
For all of the foregoing reasons, independent claims 19 and 30-33 are not directed to an improvement to the performance of a computer and are not therefore directed to patent-eligible subject matter under 35 U.S.C. 101.
Information Disclosure Statement
The information disclosure statement filed on May 14, 2026 complies with the provisions of 37 CFR 1.97, 1.98 and MPEP § 609. It has been placed in the application file. The information referred to therein has been considered as to the merits.
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 19-26 and 30-35 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract without significantly more.
Step 1, Statutory Category:
Claims 19-26 and 30 are directed to a method
Claim 31 is directed to an apparatus.
Claim 32 is directed to a non-transitory computer readable medium.
Claims 33-35 are directed to a network.
Therefore, claims 19-26 and 30-35 fall into at least one of the four statutory categories of invention, i.e., process, machine, manufacture, or composition of matter.
Step 2A, Prong One (Judicial exception recited)
The limitation “determining a posterior distribution over combinations of one or more modules of the set of modules through the PGM, based on the provided sets of inputs and sets of outputs” in claims 19, 31 and 32, as drafted this recites a mental process as a form of evaluation or judgement or opinion. One can mentally judge/evaluate the posterior distribution over combinations of one or more modules of the set of modules through the PGM, this also reflects an opinion as the mental judgement of what ' posterior distribution ' based on the provided sets of inputs and sets of outputs.
Step 2A, Prong Two (Integrated into a practical application):
This judicial exception is not integrated into a practical application. In particular, the claims recite the following additional elements:
That the method is "implemented by a computing system” is a high-level recitation of a generic computer components and represents mere instructions to apply on a computer as in MPEP 2106.05(f), which does not provide integration into a practical application.
The limitation “providing a network with sets of inputs and sets of outputs, wherein each set of inputs of the sets of inputs mapping to one of the sets of outputs corresponding to the set of inputs based on visual information on the set of inputs, and wherein the network includes a Probabilistic Generative Model (PGM) and a set of modules” amounts to data-gathering steps which is considered to be insignificant extra-solution activity, (See MPEP 2106.05(g)).
The limitation “applying domain knowledge as one or more posterior regularization constraints on the determined posterior distribution” recites insignificant extra-solution activity; and amounts to nothing more than an instruction to apply the abstract idea using a generic computer and does not render an abstract idea eligible.
The limitation “a memory; at least one processor and non-transitory computer readable medium” are recited at a high level of generality such that they amount to on more than mere instructions to apply the exception using a generic component. (see MPEP 2106.05(f)). These limitations can also be viewed as nothing more than an attempt to generally link the use of the judicial exception to the technological environment of a computer (see MPEP 2106.05(h)). Note, the mere instructions to apply an exception on a generic computer cannot integrate a judicial exception into a practical application.
At Step 2B:
The conclusions for the mere implementation using a computer are carried over and does not provide significantly more.
With respect to the “providing ….” identified as insignificant extra-solution activity above when re-evaluated this element is well-understood, routine, and conventional as evidenced by the court cases in MPEP 2106.05(d)(II), "i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); … OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network);" and thus remains insignificant extra-solution activity that does not provide significantly more.
With respect to the "applying domain knowledge ……” identified as insignificant extra-solution activity above when re-evaluated this element is well-understood, routine, and conventional in displaying information as evidenced by the court cases in MPEP 2106.05(d)(II), Intellectual Ventures I LLC v. Capital One Bank (USA), 792 F.3d 1363, 1367, 115 USPQ2d 1636, 1639 (Fed. Cir. 2015). In contrast, a claim that purports to improve computer capabilities or to improve an existing technology may integrate a judicial exception into a practical application or provide significantly more. McRO, Inc. v. Bandai Namco Games Am. Inc., 837 F.3d 1299, 1314-15, 120 USPQ2d 1091, 1101-02 (Fed. Cir. 2016); Enfish, LLC v. Microsoft Corp., 822 F.3d 1327, 1335-36, 118 USPQ2d 1684, 1688-89 (Fed. Cir. 2016)
With respect to the “a memory; at least one processor and non-transitory computer readable medium” amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields, as demonstrate by: Relevant court decision: the followings are examples of court decisions demonstrating well-understood, routine and conventional activities, see e.g., MPEP 2106.05(d)(II) and MPEP 2106.05(f)(2): Computer readable storage media comprising instructions to implement a method, e.g., see Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015).
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements when considered both individually and as an ordered combination do not amount to significantly more than the abstract idea.
Looking at the claim as a whole does not change this conclusion and the claim appears to be ineligible.
Accordingly, claim 19 is directed to an abstract idea. The remaining independent claim 31 and 32 fall short the 35 USC 101 requirement under the same rationale.
Claim 20 recites “wherein the one or more posterior regularization constraints are grouped into one or more groups of constraints according to one or more aspects of the domain knowledge”. This limitation, as drafted, is a process that, under its broadest reasonable interpretation, covers a mental process as a form of evaluation or judgement. There is no additional elements recited which tie the abstract idea into a practical application and does not amount to significant more than the identified judicial exception.
Claim 21 recites “wherein the one or more aspects of the domain knowledge include one or more of: logical reasoning, and/or temporal reasoning, and/or spatial reasoning, and/or arithmetical reasoning”. This limitation, as drafted, is a process that, under its broadest reasonable interpretation, covers a mental process as a form of evaluation or judgement. There is no additional elements recited which tie the abstract idea into a practical application and does not amount to significant more than the identified judicial exception.
Claim 22 recites “wherein the one or more posterior regularization constraints are one or more First-Order Logic (FOL) constraints”. This limitation, as drafted, is a process that, under its broadest reasonable interpretation, covers a mental process as a form of evaluation or judgement. There is no additional elements recited which tie the abstract idea into a practical application and does not amount to significant more than the identified judicial exception.
Claim 23 recites “wherein the one or more FOL constraints are generated based on at least one of: relation types of the sets of inputs, and/or object types of the sets of inputs, and/or attribute types of the sets of inputs”. This limitation, as drafted, is a process that, under its broadest reasonable interpretation, covers a mental process as a form of evaluation or judgement. There is no additional elements recited which tie the abstract idea into a practical application and does not amount to significant more than the identified judicial exception.
Claim 24 recites “wherein each of the combinations of one or more modules of the set of modules includes a modularized network, the modularized network is assembled from one or more modules of the set of modules with a structure indicating the assembled one or more modules and connections therebetween”. This limitation, as drafted, is a process that, under its broadest reasonable interpretation, covers a mental process as a form of evaluation or judgement. There is no additional elements recited which tie the abstract idea into a practical application and does not amount to significant more than the identified judicial exception.
Claim 25 recites “determining a posterior distribution over structures of modularized networks through the PGM, based on the provided sets of inputs and sets of outputs”. This limitation, as drafted, is a process that, under its broadest reasonable interpretation, covers a mental process as a form of evaluation or judgement. There is no additional elements recited which tie the abstract idea into a practical application and does not amount to significant more than the identified judicial exception.
Claim 26 recites “determining, through the PGM, a posterior distribution over structures of modularized networks indicating types of the assembled one or more modules and connections therebetween, based on the provided sets of inputs and sets of outputs”. This limitation, as drafted, is a process that, under its broadest reasonable interpretation, covers a mental process as a form of evaluation or judgement. There is no additional elements recited which tie the abstract idea into a practical application and does not amount to significant more than the identified judicial exception.
Claims 27-29 are integrated into a practical application that render claims 27-29 eligible under 35 USC 101.
As to claim 30
At Step 2A, Prong One:
The limitation “generating a combination of one or more modules of the set of modules based on a posterior distribution over combinations of one or more modules of the set of modules and the set of input images, wherein the posterior distribution is formulated by the PGM trained under domain knowledge as one or more posterior regularization constraints” in claim 30, as drafted this recites a mental process as a form of evaluation or judgement or opinion. One can mentally generate a combination of one or more modules of the set of modules based on a posterior distribution over combinations of one or more modules of the set of modules and the set of input images, this also reflects an opinion as the mental judgement of what ' posterior distribution ' based on the formulated by the PGM trained under domain knowledge as one or more posterior regularization constraints.
The limitation “selecting a candidate image from the set of candidate images based on a score of each candidate image in the set of candidate images estimated by the processing” in claim 30, as drafted this recites a mental process as a form of evaluation or judgement and/or a math calculation. One can mentally divide a first value by a second value. Additionally, computing a score of each candidate image is a math calculation.
Step 2A, Prong Two (Integrated into a practical application):
This judicial exception is not integrated into a practical application. In particular, the claims recite the following additional elements:
That the method is "implemented by a computing system” is a high-level recitation of a generic computer components and represents mere instructions to apply on a computer as in MPEP 2106.05(f), which does not provide integration into a practical application.
The limitation “providing the network with a set of input images and a set of candidate images” amounts to data-gathering steps which is considered to be insignificant extra-solution activity, (See MPEP 2106.05(g)).
The limitation “processing the set of input images and the set of candidate images through the generated combination of one or more modules” amounts to data-gathering steps which is considered to be insignificant extra-solution activity, (See MPEP 2106.05(g)).
The limitation “selecting a candidate image from the set of candidate images based on a score of each candidate image in the set of candidate images estimated by the processing” amounts to data-gathering steps which is considered to be insignificant extra-solution activity, (See MPEP 2106.05(g)).
Step 2B (claim provides an inventive concept):
The conclusions for the mere implementation using a computer are carried over and does not provide significantly more.
With respect to the “providing …; processing …; and selecting …” identified as insignificant extra-solution activity above when re-evaluated this element is well-understood, routine, and conventional as evidenced by the court cases in MPEP 2106.05(d)(II), "i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); … OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network);" and thus remains insignificant extra-solution activity that does not provide significantly more.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements when considered both individually and as an ordered combination do not amount to significantly more than the abstract idea.
Looking at the claim as a whole does not change this conclusion and the claim appears to be ineligible.
Accordingly, claim 30 is directed to an abstract idea.
Claims 33-35 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claims 33-35 do not fall within at least one of the four categories of patent eligible subject matter because claim 33 recites a plurality of modules coupled to Probabilistic Generative model (PGM). Such plurality of modules can be software and do not embed into a physical structure that would qualify as a physical device having a memory and processor to perform the operation set forth in the claim. Therefore claim 33 is a software per se and fails to fall within any statutory category subject matter under 35 USC 101.
Claims 34-35 are rejected for incorporating the deficiency of their respective base claim/s by dependency.
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 33-35 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 33 recites “a set of modules, wherein each module of the set of modules being implemented as a neural network and having at least one trainable parameters for focusing the module on one or more variable image properties”. It is unclear how a set of modules would be implemented to have a trainable parameters to focus the module on one or more variable image properties; and what would be trainable parameters that are required to focus on one or more variable image properties and for what purpose. It is also unclear as to what the applicant means by focusing on one or more variable image properties.
The claim also recites “a Probabilistic Generative Model (PGM) coupled to the set of modules, wherein the PGM is configured to output a posterior distribution over combinations of one or more modules of the set of modules”. It is unclear how the Probabilistic Generative Model (PGM) would configure to output a posterior distribution over combinations of one or more modules of the set of modules.
Claim 34 recites “wherein each of the set of modules is configured to perform a pre-designed type of process on the one or more variable image properties, and the one or more variable image properties are resulted from processing an image feature map through the at least one trainable parameters”. It is unclear as to what type of pre-designed process on the one or more variable image properties that applicant is referring to.
Claim 35 recites “wherein the one or more variable image properties includes one or more of: shape, and/or line, and/or size, and/or type, and/or color, and/or position, and/or number, and the pre-designed type of process includes logical AND, or logical OR, or logical XOR, or arithmetic ADD, or arithmetic SUB, or arithmetic MUL, or spatial STRUC, or temporal PROG, or temporal ID. It is unclear as to what the applicant means by the variable image properties includes one or more of: shape, and/or line, and/or size, and/or type, and/or color, and/or position, and/or number, and the pre-designed type of process includes logical AND, or logical OR, or logical XOR, or arithmetic ADD, or arithmetic SUB, or arithmetic MUL, or spatial STRUC, or temporal PROG, or temporal ID.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 33-35 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Marra et al., (hereinafter “Marra”) article entitled “Integrating Learning an reasoning with Deep Logic Models”.
As to claim 33, Marra discloses a network, comprising:
a set of modules, wherein each module of the set of modules being implemented as a neural network and having at least one trainable parameters for focusing the module on one or more variable image properties (page 5 and 8, unlike standard Neural networks which compute the output via a single forward pass, the output computation in a DLM can be decomposed into two stages: a low-level stage processing the input patterns, and a subsequent semantic stage, expressing constraints over the output and performing higher level reasoning. We indicate by y = {y₁ yₙ} and by f = {f₁ fn} the two multivariate random variables corresponding to the output of the model and to the output of the first stage respectively, where n > 0 denotes the dimension of the model outcomes. Assuming that the input data is processed using neural networks, the model parameters can be split into two independent components Θ = {w, 1}, where w is the vector of weights of the networks fnn and 1 is the vector of weights of the second stage, controlling the semantic layer and the constraint enforcement. Figure 1 shows the graphical dependencies among the stochastic variables that are involved in our model. The first layer processes the inputs returning the values f using a model with parameters w. The higher layer takes as input f and applies reasoning using a set of constraints, whose parameters are indicated as X, then it returns the set of output variables y; and
Data: Input data X, output targets Yₜ, function models with weights w Result: Trained model parameters Θ = {\, Initialize i = 0, X = 0, = random w; while not converged ^ i < max_iterations do Compute function outputs ƒₙₙ on X using current function weights w; Compute MAP solution = argmaxy Compute gradient Update Θ via gradient descent: V₀C₀(yₜ,YM,X); Set i = i + 1;
end
Algorithm 1. Iterative algorithm to train the function weights w and the constraint weights A.
a maximization into a minimization problem, yields the following cost function, given the current MAP solution:
C.
Minimizing X) is a local approximation of the full likelihood maximization for the current MAP solution. Therefore, the training process alter- nates the computation of the MAP solution, the computation of the gradient for X) and one weight update step as summarized by Algorithm 1. For any constraint c, the parameter 1c admits also a negative value. This is in case the c-th constraint turns out to be also satisfied by the actual MAP solution with respect to the satisfaction degree on the training data); and
a Probabilistic Generative Model (PGM) coupled to the set of modules, wherein the PGM is configured to output a posterior distribution over combinations of one or more modules of the set of modules (see pages 519-529, To model a task using DLMs there are some common design choices regard- ing these two features that one needs to take. We use the current example to show them. The first choice is to individuate the constants of the problem and their sensory representation in the perceptual space. Depending on the problem, the constants can live in a single or multiple separate domains. In the pairs example, the images are constants and each one is represented as a vector of pixel brightnesses like commonly done in deep learning.
The second choice is the selection of the predicates that should predict some characteristic over the constants and their implementation. In the pairs experiment, the predicates are the membership functions for single digits (e.g. one (x), two (x), etc.). A single neural network with 1 hidden layer, 10 hidden neurons and 10 outputs, each one mapped to a predicate, was used in this toy experiment. The choice of a small neural network is due to the fact that the goal is not to get the best possible results, but to show how the prior knowledge can help a classifier to improve its decision. In more complex experiments, different net- works can be used for different sets of predicates, or each use a separate network for each predicate.
Finally, the prior knowledge is selected. In the pairs dataset, where the constants are grouped in pairs, it is natural to express the correlations among two images in a pair via the prior knowledge. Therefore, the knowledge consists of 100 rules in the form V(x,y) D₁ (x) D₂(y), where (x,y) is a generic pair of images and (D₁, D₂) range over all the possible pairs of digit classes.
We performed the experiments with P1 = 0.9, P₂ = 0.07, P₃ = P4 = P5 = 0.01. All the images are rotated with a random degree between 0 and 90 anti-clockwise to increase the complexity of the task. There is a strong regularity in having two images representing the same digit in a pair, even some rare deviations from this rule are possible. Moreover, there are some inadmissible pairs, i.e. those containing mixed even-odd digits. The train and test sets are built by sampling 90% and 10% image pairs.).
As to claim 34, Marra discloses the claimed wherein each of the set of modules is configured to perform a pre-designed type of process on the one or more variable image properties, and the one or more variable image properties are resulted from processing an image feature map through the at least one trainable parameters (see pages 519-529).
As to claim 35, Marra discloses the claimed wherein the one or more variable image properties includes one or more of: shape, and/or line, and/or size, and/or type, and/or color, and/or position, and/or number, and the pre-designed type of process includes logical AND, or logical OR, or logical XOR, or arithmetic ADD, or arithmetic SUB, or arithmetic MUL, or spatial STRUC, or temporal PROG, or temporal ID (see pages 519-529).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
20040095374 (involved in automatically generating a layered representation of image sequence).
US 20070104383 (involved in evaluating frames of an input image sequence and automatically learns probabilistic numbers of objects to be identified in each frame and layers per frame. The sequence is then decomposed into the learned number of objects and layers. A stabilized output image sequence is then constructed by using the objects and layers from two or more frames of the input sequence to create a composite sequence of stabilized image frames. Corresponding objects and layers are transformed to construct a sequential stabilized alignment of objects and layers between frames of the stabilized sequence.)
US20070024635 (involved in constructing a generative model from automatically learned layered image sprites. An illumination model is constructed for each object in the input sequence from image frames. The image frames are decomposed into intrinsic images, illumination constants, sprite appearances, masks and sprite transformations. Uniform illumination models are applied to the corresponding object appearance models to construct the corresponding uniformly illuminated object appearance models for the generative model).
US20030235341 (involved in obtaining position information for discrete regions on a head and body part of a subject and on a background behind the subject. The image is segmented into objects corresponding to the head and body part of the subject. A position and a shape of the head and body part of the subject are identified and compression schemes are applied to the segments of the image.)
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JEAN M CORRIELUS whose telephone number is (571)272-4032. The examiner can normally be reached Monday-Friday 6:30a-10p(Midflex).
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, Ann J Lo can be reached at (571)272-9767. 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.
/JEAN M CORRIELUS/Primary Examiner, Art Unit 2159 July 30, 2026
Prosecution Insights