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 .
Status of Claims
This action is in reply to the amendments and remarks filed on 07/06/2026.
Claims 1-20 are pending.
Response to Arguments
Applicant’s arguments, with respect to the rejection(s) of claim(s) 11-20 under 35 U.S.C. 101, have been considered but they are not persuasive. The applicant argues that the claims are “directed to the operation [and training] of a specific optical neural computing architecture” and is a practical application, improvement oof the operation, and amount to significantly more; therefore, the claims overcome the 101 rejections. The examiner respectfully disagrees.
The additional elements and use in the claim do not operate to overcome the previous 101 abstract idea rejection. The recitation of “training a ring-based optical neural network” are maintained as being at a high-level and are determined to be equivalent to adding the words “apply it” (or an equivalent, i.e., “training”) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f). See 35 U.S.C 101 section for full, updated analysis of claim limitations necessitated by applicant amendments.
Applicant is encouraged to add clarifying amendments of the “ring-based optical neural network” architecture or defining specific steps/training performed by the invention so that the recitations are not at a high level.
Applicant’s arguments, with respect to the rejection(s) of claim(s) 1 under 35 U.S.C. 103, have been considered but they are not persuasive. Applicant argues that no art of reference teaches the claim language of claim 1 that states “a signal mixing component, the signal mixing component including at least a third ring resonator and a fourth ring resonator, the third ring resonator being coupled to the first waveguide, the fourth ring resonator being coupled to the second waveguide, and the third ring resonator and the fourth ring resonator being coupled to each other”, since “neither reference discloses a signal mixing mechanism in which: a resonator coupled to a first waveguide is directly coupled to a resonator coupled to a second waveguide, and signal mixing occurs via inter-resonator coupling spanning distinct waveguide paths”. Upon review of the combination of prior art, the examiner respectfully disagrees due to the broadness of the claim language.
Ohno, sections “Chip Layout”-“Experimental Setup” and Figs. 1a-b “weight matrix W is encoded into the transmittances of tunable MRRs, through which forward signals propagating in the horizontal direction are selectively coupled and multiplexed in waveguides along the vertical direction…A multimode waveguide structure including four ellipses is employed at each intersection of the MRR crossbar array to minimize its insertion loss and crosstalk.” Here, the signals in the waveguides are mixed according to the tuned and “coupled” resonators at the intersections; and is maintained as reading on the claimed resonators and waveguides since the signals are “coupled” (i.e., Fig. 1a: W11-W14). Applicant is encouraged to add clarifying amendments to the claim language cannot be read as broadly.
Further, Campo sections 1 and 3 teach in alternative “we make an analysis of a collection of 9 electro-optic interferometric systems made up of combinations of MZIs and MRRs to generate reconfigurable optical nonlinear activation functions” and these including ring resonators at different stages connected to “waveguides”.
See 35 U.S.C 103 section for full mapping of claim limitations.
In response to applicant’s arguments that there is no teaching, suggestion, or motivation to combine the references, the examiner recognizes that obviousness may be established by combining or modifying the teachings of the prior art to produce the claimed invention where there is some teaching, suggestion, or motivation to do so found either in the references themselves or in the knowledge generally available to one of ordinary skill in the art. See In re Fine, 837 F.2d 1071, 5 USPQ2d 1596 (Fed. Cir. 1988), In re Jones, 958 F.2d 347, 21 USPQ2d 1941 (Fed. Cir. 1992), and KSR International Co. v. Teleflex, Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007). In this case, Ohno and Campo are both teaching ring oscillator and waveguide combinations in activation functions for processing data in optical neural networks; thus, directed to the same inventive field of art, utilize these elements in complementary ways, and motivations to combine are listed under 35 U.S.C 103 section below.
Applicant’s arguments, with respect to the rejection(s) of claim(s) 11 under 35 U.S.C. 103, have been considered but they are not persuasive. Applicant argues that no art of reference teaches the claim language of claims 11, since “Campo's phase shift expressions describe operational tuning behavior, but are not generated characterization equations used to govern training of a ring-based optical neural network”, and “Neither Campo nor Ohno discloses or suggests a training framework in which a characterization equation of component response variation is used to drive or condition training of the network”. Upon review of the combination of prior art, the examiner respectfully disagrees due to the broadness of the claim language.
Campo, section 3 teaches “for optical neural networks” utilizing a “phase shift” equation that includes “tunable” parameters. Sections 3-4 teach “we present the proposed hardware architectures to generate nonlinear functions for optical neural networks” with the phase shift equation tuning of parameters, and “training” different types of neural networks including a MZI-ORR design. Sections 3-4 teach training an ONN and using it in combination with different types of activation functions in order to better tune the parameters of the functions. Here, Campo’s phase shift equation is taught to have tunable parameters that are included in a trainable optical neural network; thus determining the architectural tuning of the network (“based on” as claimed).
Further, Ohno sections “Chip Layout’” and “Simulation of on-Chip Backpropagation” and Figs. 4-5 teach in alternative training an ONN model “based on the MRR crossbar array” of tunable MRR’s and backpropagating to retune the values.
Applicant is encouraged to add clarifying amendments to the claim language cannot be read as broadly. See 35 U.S.C 103 section for full mapping of claim limitations.
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 11-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claim 11 is respectively drawn to a method, hence falls under one of four categories of statutory subject matter (Step 1). Nonetheless, the claims are directed to a judicially recognized exception of an abstract idea without significantly more.
Claim 11 recite the following, or analogous, limitations “generating a characterization equation that describes a variation in a response of a component with respect to at least one tunable parameter of the component;…and generating a value for the at least one tunable parameter based on the training and the task. These limitations, as claimed, under its broadest reasonable interpretation, can be evaluated in a human mind, except for the recitation of generic computer components (using artificial intelligence/machine learning, a computer including one or more microprocessors, and a non-transitory computer readable storage medium) (Step 2A). Other than reciting “training a ring-based optical neural network for a task based on the characterization equation, the ring-based optical neural network including the component” to perform the exceptions, nothing in the claims preclude the steps from practically being performed in the human mind. For example, a human expert can:
mentally/with the aid of pen and paper generating a characterization equation that describes a variation in a response of a component with respect to at least one tunable parameter of the component (e.g. by thinking of/writing out a calculation to output a change in a variable of an element),
mentally/with the aid of pen and paper generating a value for the at least one tunable parameter based on the training and the task (e.g. by thinking of/writing out a numerical value for the variable from the tuning and purpose).
Thus, the claims recite a mental process (Step 2A, Prong 1).
Claim 11 include additional elements, “training a ring-based optical neural network for a task based on the characterization equation, the ring-based optical neural network including the component”, however the recitations of these elements are at a high level of generality, and amount to adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer (i.e., training a ring-based optical neural network for a task based on the characterization equation) (see MPEP 2106.05(f)), and generally link the use of the judicial exception to a particular technological environment or field of use (i.e., the ring-based optical neural network including the component) (see MPEP 2106.05(h)). These do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea (Step 2A, Prong 2; see MPEP 2106.05(f)). The additional elements in the claim do not amount to significantly more than an abstract idea. Furthermore, the claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the additional elements of using “training a random forest model with the aggregated log data and the aggregated performance indicator data to”, “for a plurality of computing devices”, “at least one processor; and memory storing instruction” to perform the steps of the independent claim amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer and generally link the use of the judicial exception to a particular technological environment or field of use, and cannot provide an inventive concept. (STEP 2B). As such, claim 11 is not patent eligible.
Dependent claims 12-20 are also ineligible for the same reasons given with respect to claim 11. The dependent claims describe additional mental processes:
mentally/with the aid of pen and paper assigning the value to the at least one tunable parameter (claim 12) (e.g. by mentally/writing out the output numerical value for the variable)
mentally/with the aid of pen and paper wherein the component is a linear component (claim 13) (e.g. by mentally/writing out a linear element)
mentally/with the aid of pen and paper wherein the linear component includes a phase tuning component (claim 14) (e.g. by mentally/writing out a linear phase changing element)
mentally/with the aid of pen and paper wherein the linear component includes a signal mixing component (claim 15) (e.g. by mentally/writing out a linear response combination element)
mentally/with the aid of pen and paper wherein the component is a non-linear component (claim 16) (e.g. by mentally/writing out the element is nonlinear)
mentally/with the aid of pen and paper wherein the non-linear component includes a directional coupler (claim 17) (e.g. by mentally/writing out a nonlinear forward moving coupling function)
mentally/with the aid of pen and paper wherein the non-linear component includes an optical modulator (claim 18) (e.g. by mentally/writing out a nonlinear optical modulation function)
Again, the dependent claims continued to cover the performance of the limitation in the mind as inherited from the independent claims (Step 2A, Prong 1). The dependent claim 19 recitation of “wherein the ring-based optical neural network includes a first waveguide and a second waveguide, the first waveguide being spaced from the second waveguide”, and claim 20 recitation of “wherein the first waveguide is parallel to the second waveguide”, are again recited at a high level and amount to generally link the use of the judicial exception to a particular technological environment or field of use (see MPEP 2106.05(h)), and do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea (Step 2A, Prong 2; see MPEP 2106.05(h)). The additional element in the claims do not amount to significantly more than an abstract idea. As discussed above with respect to the integration of the abstract idea into a practical application, the additional elements to perform the steps of in the dependent claims and perform the steps of the claims amount to no more than generally link the use of the judicial exception to a particular technological environment or field of use, and cannot provide an inventive concept. (STEP 2B). As such, dependent claims 2-20 do not amount to significantly more than an abstract idea nor provide any inventive concept, therefore are not patent eligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
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.
Claims 1-10 are rejected under 35 U.S.C. 103 as being unpatentable over Ohno et al (“Si Microring Resonator Crossbar Array for On-Chip Inference and Training of the Optical Neural Network”, 2022) hereinafter Ohno, in view of Campo et al (“Reconfigurable Activation Functions in Integrated Optical Neural Networks” 2022) hereinafter Campo.
Regarding claim 1, Ohno teaches a system comprising:
a first waveguide and a second waveguide, the first waveguide being spaced from the second waveguide (section “Chip Layout” and Figs. 1a-b teach “weight matrix W is encoded into the transmittances of tunable MRRs, through which forward signals propagating in the horizontal direction are selectively coupled and multiplexed in waveguides along the vertical direction… After a similar encoding process by the other MZI modulator array, the optical signals from Ports 5−8 are selectively multiplexed in waveguides along the horizontal direction through the MRR crossbar array”. Here, multiple waveguides are depicted in a grid formation.);
a first phase tuning component, the first phase tuning component including a first ring resonator coupled to the first waveguide (sections “Chip Layout”-“Experimental Setup” and Figs. 1a-b teaches “Thermo-optic (TO) phase shifters made of TiN thin-film heaters are used to tune the MRRs and MZIs”; wherein each waveguide is depicted with microring resonators on their path.);
a second phase tuning component, the second phase tuning component including a second ring resonator coupled to the second waveguide (sections “Chip Layout”-“Experimental Setup” and Figs. 1a-b teaches “Thermo-optic (TO) phase shifters made of TiN thin-film heaters are used to tune the MRRs and MZIs”; wherein each waveguide is depicted with microring resonators on their path.); and
a signal mixing component, the signal mixing component including at least a third ring resonator and a fourth ring resonator, the third ring resonator being coupled to the first waveguide, the fourth ring resonator being coupled to the second waveguide, and the third ring resonator and the fourth ring resonator being coupled to each other (sections “Chip Layout”-“Experimental Setup” and Figs. 1a-b “weight matrix W is encoded into the transmittances of tunable MRRs, through which forward signals propagating in the horizontal direction are selectively coupled and multiplexed in waveguides along the vertical direction…A multimode waveguide structure including four ellipses is employed at each intersection of the MRR crossbar array to minimize its insertion loss and crosstalk.” Here, the signals in the wave guides are mixed according to the tuned and “coupled” resonators at the intersections.).
Ohno at least implies a signal mixing component, the signal mixing component including at least a third ring resonator and a fourth ring resonator, the third ring resonator being coupled to the first waveguide, the fourth ring resonator being coupled to the second waveguide, and the third ring resonator and the fourth ring resonator being coupled to each other (see mappings above); however, Campo teaches a signal mixing component, the signal mixing component including at least a third ring resonator and a fourth ring resonator, the third ring resonator being coupled to the first waveguide, the fourth ring resonator being coupled to the second waveguide, and the third ring resonator and the fourth ring resonator being coupled to each other (sections 1 and 3 teach “we make an analysis of a collection of 9 electro-optic interferometric systems made up of combinations of MZIs and MRRs to generate reconfigurable optical nonlinear activation functions” and these including ring resonators at different stages connected to “waveguides”).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to implement Campo’s teachings of ring resonator activation functions connected to waveguides into Ohno‘s teaching of a “Fully integrated MRR array” including MZI modulators and activation functions in order to utilize ring resonator activation functions for better results accuracies (Campo, sections 1, 3, and 5).
Regarding claim 2, the combination of Ohno and Campo teach all the claim limitations of claim 1 above; and further teach wherein the first waveguide is parallel to the second waveguide (Ohno, section “Chip Layout” and Figs. 1a-b teach “forward signals propagating in the horizontal direction are selectively coupled and multiplexed in waveguides along the vertical direction…After a similar encoding process by the other MZI modulator array, the optical signals from Ports 5−8 are selectively multiplexed in waveguides along the horizontal direction through the MRR crossbar array”. Here, multiple waveguides are depicted in a grid formation.).
Regarding claim 3, the combination of Ohno and Campo teach all the claim limitations of claim 1 above; and further teach wherein the first ring resonator is tunable (Ohno, sections “Chip Layout”-“Experimental Setup” and Figs. 1a-b teaches “Thermo-optic (TO) phase shifters made of TiN thin-film heaters are used to tune the MRRs and MZIs”; wherein each waveguide is depicted with microring resonators on their path.).
Regarding claim 4, the combination of Ohno and Campo teach all the claim limitations of claim 1 above; and further teach wherein the second ring resonator is tunable (Ohno, sections “Chip Layout”-“Experimental Setup” and Figs. 1a-b teaches “Thermo-optic (TO) phase shifters made of TiN thin-film heaters are used to tune the MRRs and MZIs”; wherein each waveguide is depicted with microring resonators on their path.).
Regarding claim 5, the combination of Ohno and Campo teach all the claim limitations of claim 1 above; and further teach a first non-linear activation component, the first non-linear activation component including a first directional coupling component and a first optical modulating component (Ohno, section “Simulation of on-Chip Backpropagation” and Figs. 1 and 4 teach ReLU function between input and hidden layers), the first directional coupling component including a fifth ring resonator and the first optical modulating component including a sixth ring resonator (Campo, sections 1 and 3 teach tunable parameters for different configurations of the “MZIs and MRRs to generate reconfigurable optical nonlinear activation functions”. Further that “[c]oupling can be made using directional couplers (DC), multimode interferometers (MMI), or MZIs if the ki is defined to be tunable. The φi represent phase shifts in the waveguide. These shifts can be implemented using thermo-optic phase shifters, micro electromechanical (MEMS) phase shifters or phase shifters based in phase change materials (PCM). Subindex r is used to indicate that the correspondent element is part of a ring resonator”, where the phase shifters “perform the self-phase modulation”); and
a second non-linear activation component, the second non-linear activation component including a second directional coupling component and a second optical modulating component (Ohno, section “Simulation of on-Chip Backpropagation” and Figs. 1 and 4 teach Softmax layer function at the output layer), the second directional coupling component including a seventh ring resonator and the second optical modulating component including an eighth ring resonator (Campo, sections 1 and 3 teach tunable parameters for different configurations of the “MZIs and MRRs to generate reconfigurable optical nonlinear activation functions”. Further that “[c]oupling can be made using directional couplers (DC), multimode interferometers (MMI), or MZIs if the ki is defined to be tunable. The φi represent phase shifts in the waveguide. These shifts can be implemented using thermo-optic phase shifters, micro electromechanical (MEMS) phase shifters or phase shifters based in phase change materials (PCM). Subindex r is used to indicate that the correspondent element is part of a ring resonator”, where the phase shifters “perform the self-phase modulation”).
Ohno and Campo are combinable for the same rationale as set forth above with respect to claim 1.
Regarding claim 6, the combination of Ohno and Campo teach all the claim limitations of claim 5 above; and further teach wherein at least one of the fifth ring resonator and the sixth ring resonator is tunable (Campo, sections 1 and 3 teach tunable parameters for different configurations of the “MZIs and MRRs to generate reconfigurable optical nonlinear activation functions”. Further that “[c]oupling can be made using directional couplers (DC), multimode interferometers (MMI), or MZIs if the ki is defined to be tunable. The φi represent phase shifts in the waveguide. These shifts can be implemented using thermo-optic phase shifters, micro electromechanical (MEMS) phase shifters or phase shifters based in phase change materials (PCM). Subindex r is used to indicate that the correspondent element is part of a ring resonator”).
Ohno and Campo are combinable for the same rationale as set forth above with respect to claim 1.
Regarding claim 7, the combination of Ohno and Campo teach all the claim limitations of claim 5 above; and further teach wherein at least one of the seventh ring resonator, and the eighth ring resonator is tunable (Campo, sections 1 and 3 teach tunable parameters for different configurations of the “MZIs and MRRs to generate reconfigurable optical nonlinear activation functions”. Further that “[c]oupling can be made using directional couplers (DC), multimode interferometers (MMI), or MZIs if the ki is defined to be tunable. The φi represent phase shifts in the waveguide. These shifts can be implemented using thermo-optic phase shifters, micro electromechanical (MEMS) phase shifters or phase shifters based in phase change materials (PCM). Subindex r is used to indicate that the correspondent element is part of a ring resonator”).
Ohno and Campo are combinable for the same rationale as set forth above with respect to claim 1.
Regarding claim 8, Ohno teaches a system, comprising:
a waveguide (section “Chip Layout” and Figs. 1a-b teach “weight matrix W is encoded into the transmittances of tunable MRRs, through which forward signals propagating in the horizontal direction are selectively coupled and multiplexed in waveguides along the vertical direction… After a similar encoding process by the other MZI modulator array, the optical signals from Ports 5−8 are selectively multiplexed in waveguides along the horizontal direction through the MRR crossbar array”. Here, multiple waveguides are depicted in a grid formation.); and
a non-linear activation component (section “Simulation of on-Chip Backpropagation” teaches “we have numerically revealed that the proposed on-chip backpropagation using the MRR crossbar array can be used to train ONNs regardless of the nonlinear transmission characteristics of an MRR”. Here, it is taught that the “Fully integrated MRR array” functions are nonlinear.), the non-linear activation component including:
a directional coupling component, the directional coupling component including a first ring resonator coupled to the waveguide (sections “Chip Layout”-“Experimental Setup” and Figs. 1a-b teaches “Thermo-optic (TO) phase shifters made of TiN thin-film heaters are used to tune the MRRs and MZIs”; wherein each waveguide is depicted with microring resonators on their path.); and
an optical modulating component, the optical modulation component including a second ring resonator coupled to the waveguide (sections “Chip Layout”-“Experimental Setup” and Figs. 1a-b teach the “Fully integrated MRR crossbar array” including a backward signal MZI modulator connected to ring resonators of the waveguides).
Ohno at least implies the non-linear activation component including:…an optical modulating component, the optical modulation component including a second ring resonator coupled to the waveguide (see mappings above); however, Campo teaches the non-linear activation component including:…an optical modulating component, the optical modulation component including a second ring resonator coupled to the waveguide (sections 1 and 3 teach tunable parameters for different configurations of the “MZIs and MRRs to generate reconfigurable optical nonlinear activation functions”. Further that “[c]oupling can be made using directional couplers (DC), multimode interferometers (MMI), or MZIs if the ki is defined to be tunable. The φi represent phase shifts in the waveguide. These shifts can be implemented using thermo-optic phase shifters, micro electromechanical (MEMS) phase shifters or phase shifters based in phase change materials (PCM). Subindex r is used to indicate that the correspondent element is part of a ring resonator”, where the phase shifters “perform the self-phase modulation”).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to implement Campo’s teachings of ring resonator activation functions connected to waveguides into Ohno‘s teaching of a “Fully integrated MRR array” including MZI modulators and activation functions in order to utilize ring resonator activation functions for better results accuracies (Campo, sections 1, 3, and 5).
Regarding claim 9, the combination of Ohno and Campo teach all the claim limitations of claim 8 above; and further teach wherein the first ring resonator is tunable (Ohno, sections “Chip Layout”-“Experimental Setup” and Figs. 1a-b teaches “Thermo-optic (TO) phase shifters made of TiN thin-film heaters are used to tune the MRRs and MZIs”; wherein each waveguide is depicted with microring resonators on their path.).
Regarding claim 10, the combination of Ohno and Campo teach all the claim limitations of claim 8 above; and further teach wherein the second ring resonator is tunable (Ohno, sections “Chip Layout”-“Experimental Setup” and Figs. 1a-b teaches “Thermo-optic (TO) phase shifters made of TiN thin-film heaters are used to tune the MRRs and MZIs”; wherein each waveguide is depicted with microring resonators on their path.).
Claims 11-20 are rejected under 35 U.S.C. 103 as being unpatentable over Campo et al (“Reconfigurable Activation Functions in Integrated Optical Neural Networks” 2022) hereinafter Campo, in view of Ohno et al (“Si Microring Resonator Crossbar Array for On-Chip Inference and Training of the Optical Neural Network”, 2022) hereinafter Ohno.
Regarding claim 11, Campo teaches a method, comprising:
generating a characterization equation that describes a variation in a response of a component with respect to at least one tunable parameter of the component (section 3 teaches “for optical neural networks” utilizing a “phase shift” equation that includes “tunable” parameters);
training a ring-based optical neural network for a task based on the characterization equation, the ring-based optical neural network including the component (sections 3-4 teaches “we present the proposed hardware architectures to generate nonlinear functions for optical neural networks” with the phase shift equation tuning of parameters, and “training” different types of neural networks including a MZI-ORR design); and
generating a value for the at least one tunable parameter based on the training and the task (sections 3-4 teach training an ONN and using it in combination with different types of activation functions in order to better tune the parameters of the functions).
Campo at least implies generating a value for the at least one tunable parameter based on the training and the task (see mappings above); however, Ohno teaches generating a value for the at least one tunable parameter based on the training and the task (sections “Chip Layout’” and “Simulation of on-Chip Backpropagation” and Figs. 4-5 teach training an ONN model “based on the MRR crossbar array” of tunable MRR’s and backpropagating to retune the values).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to implement Ohno‘s teaching of a “Fully integrated MRR array” including MZI modulators and activation functions and tuning MRR array values through back propagation into Campo’s teachings of ring resonator activation functions connected to waveguides in order to reduce “computation time” and “accelerate the training process” (Ohno, sections “Chip Layout”, “Simulation of on-Chip Backpropagation”, and “Benchmark”).
Regarding claim 12, the combination of Campo and Ohno teach all the claim limitations of claim 11 above; and further teach assigning the value to the at least one tunable parameter (Campo, sections 3-4 teach training an ONN and using it in combination with different types of activation functions in order to better tune the parameters of the functions).
Regarding claim 13, the combination of Campo and Ohno teach all the claim limitations of claim 11 above; and further teach wherein the component is a linear component (Ohno, sections “Simulation of on-Chip Backpropagation”-“Benchmark” and Fig. 5 teach “the Q-factor increases linearly in the figure”).
Campo and Ohno are combinable for the same rationale as set forth above with respect to claim 11.
Regarding claim 14, the combination of Campo and Ohno teach all the claim limitations of claim 13 above; and further teach wherein the linear component includes a phase tuning component (Ohno, sections “Simulation of on-Chip Backpropagation”-“Benchmark” and Fig. 5 teach “the Q-factor increases linearly in the figure” as the “Calculated relationship between the circuit size of MRR crossbar array and the required Q-factor of MRR”, being the included tunable MMR’s).
Campo and Ohno are combinable for the same rationale as set forth above with respect to claim 11.
Regarding claim 15, the combination of Campo and Ohno teach all the claim limitations of claim 13 above; and further teach wherein the linear component includes a signal mixing component (Ohno, sections “Simulation of on-Chip Backpropagation”-“Benchmark” and Fig. 5 teach “the Q-factor increases linearly in the figure” as the “Calculated relationship between the circuit size of MRR crossbar array and the required Q-factor of MRR”, being the included tunable MMR’s. Further, sections “Chip Layout”-“Experimental Setup” and Figs. 1a-b “weight matrix W is encoded into the transmittances of tunable MRRs, through which forward signals propagating in the horizontal direction are selectively coupled and multiplexed in waveguides along the vertical direction…A multimode waveguide structure including four ellipses is employed at each intersection of the MRR crossbar array to minimize its insertion loss and crosstalk.” Here, the signals in the wave guides are mixed according to the tuned and “coupled” resonators at the intersections.).
Campo and Ohno are combinable for the same rationale as set forth above with respect to claim 11.
Regarding claim 16, the combination of Campo and Ohno teach all the claim limitations of claim 11 above; and further teach wherein the component is a non-linear component (Campo, section 3 teaches use of “nonlinear functions” wherein “[t]he control of each phase shifter enables the creation of tunable optical couplers with independent power ratio and phase shift tuning”).
Regarding claim 17, the combination of Campo and Ohno teach all the claim limitations of claim 16 above; and further teach wherein the non-linear component includes a directional coupler (Campo, section 3 teaches use of “nonlinear functions” wherein “[t]he control of each phase shifter enables the creation of tunable optical couplers with independent power ratio and phase shift tuning”).
Regarding claim 18, the combination of Campo and Ohno teach all the claim limitations of claim 16 above; and further teach wherein the non-linear component includes an optical modulator (Campo, section 3 teaches use of “nonlinear functions” wherein “[t]he control of each phase shifter enables the creation of tunable optical couplers with independent power ratio and phase shift tuning”; and “phase shifters that perform the self-phase modulation”).
Regarding claim 19, the combination of Campo and Ohno teach all the claim limitations of claim 11 above; and further teach wherein the ring-based optical neural network includes a first waveguide and a second waveguide, the first waveguide being spaced from the second waveguide (Ohno, section “Chip Layout” and Figs. 1a-b teach “weight matrix W is encoded into the transmittances of tunable MRRs, through which forward signals propagating in the horizontal direction are selectively coupled and multiplexed in waveguides along the vertical direction… After a similar encoding process by the other MZI modulator array, the optical signals from Ports 5−8 are selectively multiplexed in waveguides along the horizontal direction through the MRR crossbar array”. Here, multiple waveguides are depicted in a grid formation.).
Campo and Ohno are combinable for the same rationale as set forth above with respect to claim 11.
Regarding claim 20, the combination of Campo and Ohno teach all the claim limitations of claim 19 above; and further teach wherein the first waveguide is parallel to the second waveguide (Ohno, section “Chip Layout” and Figs. 1a-b teach “forward signals propagating in the horizontal direction are selectively coupled and multiplexed in waveguides along the vertical direction…After a similar encoding process by the other MZI modulator array, the optical signals from Ports 5−8 are selectively multiplexed in waveguides along the horizontal direction through the MRR crossbar array”. Here, multiple waveguides are depicted in a grid formation.).
Campo and Ohno are combinable for the same rationale as set forth above with respect to claim 11.
Conclusion
THIS ACTION IS MADE FINAL. 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 extension fee 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 CLINT MULLINAX whose telephone number is 571-272-3241. The examiner can normally be reached on Mon - Fri 8:00-4:30 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Alexey Shmatov can be reached on 571-270-3428. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/C.M./Examiner, Art Unit 2123
/ALEXEY SHMATOV/Supervisory Patent Examiner, Art Unit 2123
Prosecution Insights