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 .
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 2024-12-02 has been entered. The status of claims is as follows:
Claims 1 and 3-12 remain pending in the application.
Claims 1, 6, 8, and 10 are amended.
Response to Arguments
Applicant's arguments in response to rejections under 35 USC 101 have been fully considered but they are not persuasive.
Applicant argues in Remarks Page 5 that the new limitation “wherein an amount of charging potential for a next spike generation equals to the target threshold” integrates the abstract idea into a practical application.
Examiner respectfully disagrees. Setting and evaluating a threshold for an action, such as “charging potential” for “spike generation”, which could merely be calculation outputs, is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process. This is explained below in the 101 rejections.
Applicant's arguments in response to rejections under 35 USC 103 have been considered, but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: “a threshold adjusting unit” in claim 10.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof. In this case, “a threshold adjusting unit” is being interpreted as a “discharge NMOS transistor” or its equivalents, as per Specification [0048].
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Objections
Claims 1, 6, and 8 are objected to because it recites the limitation “each neuron”. It is true that one could argue that there is antecedent basis for this limitation as the preambles set forth the context of a “spiking neural network” or a “neural network”, and one of ordinary skill in the art would understand that a spiking neural network comprises neurons and thus be apprised of the scope of the invention. However, Examiner still recommends amending to clarify, for example, stating “neural network comprising a plurality of neurons” and subsequently referring to “each neuron of the plurality of neurons”.
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.
Claim 10 is 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 10 recites the limitation "the firing unit". There is insufficient antecedent basis for this limitation in the claim. Examiner is interpreting this limitation as “a firing unit”.
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 and 3-5 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1:
Claims 1 and 3-5 are directed to a method, and therefore are directed to one of the four statutory categories of patent eligible subject matter.
Step 2A Prong 1:
Claim 1 recites:
“adjusting an effective threshold for a next firing after a firing of each neuron to be the same as a target threshold in each neuron”; adjusting a threshold is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process; furthermore, Examiner notes that “firing” is not positively recited, and even if it was, the broadest reasonable reinterpretation of the term “firing” could simply be that a calculated output of a software neuron is greater than zero
“wherein adjusting an effective threshold of each neuron comprises lowering a membrane potential of each neuron by an amount of the target threshold after the firing of each neuron”; lowering a value, or “potential” which appears to merely be a type of threshold for a calculation output, by an amount is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process
“wherein an amount of charging potential for a next spike generation equals to the target threshold”; setting and evaluating a threshold for an action, such as “charging potential” for “spike generation”, which could merely be calculation outputs, is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process
Step 2A Prong 2
This judicial exception is not integrated into a practical application because the additional element is:
“A method for compensating a difference and/or a variation of a neuron threshold for a firing in a spiking neural network”; Examiner notes that “compensating a difference and/or a variation of a neuron threshold for firing” is merely an intended result of the preamble, and is thus does not limit the claim; however, the recitation of “a spiking neural network” is “necessary to give life, meaning, and vitality’ to the claim” (MPEP 2111.02); in this case, Examiner notes that a broad recitation of “a spiking neural network”, at a high level of generality, amounts to mere instructions to apply an exception (“(1) Whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished”) as per MPEP 2106.05(f); specifically, without any implementation details of the spiking neural network, the generically recited spiking neural network does not significantly limit the practice of the subsequent claimed limitations which were shown above to recite an abstract idea
Step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional element is:
“A method for compensating a difference and/or a variation of a neuron threshold for a firing in a spiking neural network”; this does not amount to significantly more than the judicial exception, for the reasons recited above in Step 2A Prong 2
Dependent Claims:
Claim 3 recites:
“a neural network is implemented in a hardware”; this limitation, without specific details about the hardware configuration, amounts to nothing more than an instruction to apply the abstract idea using a generic computer as per MPEP 2106.05(f) as per MPEP 2106.05(f) under Steps 2A Prong 2 and 2B
“wherein the target threshold is lower than a designed threshold of a neuron”; Examiner notes that as explained above in the rejection to Claim 1, adjusting a threshold is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process
Claim 4 recites:
“wherein an effective threshold for a second and all subsequent firings is set equal to the target threshold”; Examiner notes that as explained above in the rejection to Claim 1, adjusting a threshold is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process
Claim 5 recites:
“wherein the target threshold is adjusted to be less than a real threshold of the each neuron”; Examiner notes that as explained above in the rejection to Claim 1, adjusting a threshold is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process
Claims 6-7 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1:
Claims 6-7 are directed to a method, and therefore are directed to one of the four statutory categories of patent eligible subject matter.
Step 2A Prong 1:
Claim 6 recites:
“discharging a same amount of a membrane potential for each neuron after firing”; Specification [0032-0034] describes this “discharging” with equations, and is thus a mathematical concept
“wherein discharging the same amount of a membrane potential for each neuron after the firing is discharging an amount of a target threshold for each neuron after the firing”; Specification [0032-0034] describes this “discharging” with equations, and is thus a mathematical concept
“wherein an amount of charging potential for a next spike generation equals to the target threshold”; setting and evaluating a threshold for an action, such as “charging potential” for “spike generation”, which could merely be calculation outputs, is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process
Step 2A Prong 2
This judicial exception is not integrated into a practical application because the additional element is:
“A method for discharging a membrane potential after a firing of a neuron in a spiking neural network”; Examiner notes that “discharging a membrane potential after a firing of a neuron” is merely an intended result of the preamble, and is thus does not limit the claim; however, the recitation of “a spiking neural network” is “necessary to give life, meaning, and vitality’ to the claim” (MPEP 2111.02); in this case, Examiner notes that a broad recitation of “a spiking neural network”, at a high level of generality, amounts to mere instructions to apply an exception (“(1) Whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished”) as per MPEP 2106.05(f); specifically, without any implementation details of the spiking neural network, the generically recited neural network does not significantly limit the practice of the subsequent claimed limitations which were shown above to recite an abstract idea
Step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional element is:
“A method for discharging a membrane potential after a firing of a neuron in a spiking neural network”; this does not amount to significantly more than the judicial exception, for the reasons recited above in Step 2A Prong 2
Dependent Claims:
Claim 7 recites:
“wherein each neuron fires to generate a spike when a membrane potential of a time integration and accumulation of an input signal exceed a threshold”; integrating values together over time, whether that be through concatenation, addition, or some other method, is an evaluation that can be performed by a human with pen and paper, and is thus a mental process or mathematical concept
“wherein the neuron fires to generate a spike when the accumulated input signals exceed a threshold”; determining when a threshold is exceeded is a mental process; furthermore, “fires to generate a spike” could merely refer to performing a calculation or evaluation when the threshold exceeded, which is also a mental process
Claims 8-9 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1:
Claims 8-9 are directed to a method, and therefore are directed to one of the four statutory categories of patent eligible subject matter.
Step 2A Prong 1:
Claim 8 recites:
“reducing an amount of accumulated input signals by the same amount for each neuron”; reducing an amount, of generically recited “input signals”, which could merely be calculation inputs, is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process
“wherein the reducing the amount of accumulated input signals by the same amount for each neuron is reducing an amount of a target threshold for each neuron”; reducing an amount of a threshold by an amount is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process
“wherein an amount of charging potential for a next spike generation equals to the target threshold”; setting and evaluating a threshold for an action, such as “charging potential” for “spike generation”, which could merely be calculation outputs, is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process
Step 2A Prong 2
This judicial exception is not integrated into a practical application because the additional element is:
“A resetting method for a neuron for a next firing after a firing of a neuron in a neural network, the resetting comprising”; Examiner notes that “resetting … for a next firing after a firing of a neuron” is merely an intended result of the preamble, and is thus does not limit the claim; however, the recitation of “a neural network” is “necessary to give life, meaning, and vitality’ to the claim” (MPEP 2111.02); in this case, Examiner notes that a broad recitation of “a neural network”, at a high level of generality, amounts to mere instructions to apply an exception (“(1) Whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished”) as per MPEP 2106.05(f); specifically, without any implementation details of the neural network, the generically recited neural network does not significantly limit the practice of the subsequent claimed limitations which were shown above to recite an abstract idea
Step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional element is:
“A resetting method for a neuron for a next firing after a firing of a neuron in a neural network, the resetting comprising”; this does not amount to significantly more than the judicial exception, for the reasons recited above in Step 2A Prong 2
Dependent Claims:
Claim 9 recites:
“wherein the accumulated input signals are obtained by time integration of the input signals”; integrating values together over time, whether that be through concatenation, addition, or some other method, is an evaluation that can be performed by a human with pen and paper, and is thus a mental process or mathematical concept
“wherein the neuron fires to generate a spike when the accumulated input signals exceed a threshold”; determining when a threshold is exceeded is a mental process; furthermore, “fires to generate a spike” could merely refer to performing a calculation or evaluation when the threshold exceeded, which is also a mental process
Claims 10-12 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1:
Claims 10-12 are directed to a spiking neural network, which is “comprising a plurality of neurons”, in which “each neuron comprises: a threshold adjusting unit”, in which the “threshold adjusting unit” is described as “implemented by a discharge NMOS transistor” that performs actions described in Specification [0048]; therefore, the claims are directed to one of the four statutory categories of patent eligible subject matter because they are directed to a system comprising computer hardware.
Step 2A Prong 1:
Claim 10 recites:
“wherein the plurality of neurons time-integrate and accumulate an input signal and fire an output spike when the accumulated input signal exceeds a threshold”; integrating values together over time, whether that be through concatenation, addition, or some other method, is an evaluation that can be performed by a human with pen and paper, and is thus a mental process or mathematical concept; furthermore, determining that a threshold has been exceeded, and producing an “output spike”, which can merely be a calculation output, is an evaluation that can be performed by a human with pen and paper, and is thus a mental process
“wherein after firing the spike, an amount of accumulated input signals is reduced by a same amount of a target threshold for firing a next spike”; reducing an amount is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process
“reducing the amount of the accumulated input signal of the accumulation unit by the amount of a target threshold in response to the output spike of the firing unit”; reducing an amount of a value in response to a condition is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process
“wherein an amount of charging potential for a next spike generation equals to the target threshold”; setting and evaluating a threshold for an action, such as “charging potential” for “spike generation”, which could merely be calculation outputs, is an evaluation that can be performed by a human in the mind or with pen and paper, and is thus a mental process
Step 2A Prong 2
This judicial exception is not integrated into a practical application because the additional element is:
“A spiking neural network comprising a plurality of neurons … wherein each neuron comprises: a threshold adjusting unit”; a broad recitation of “a spiking neural network”, at a high level of generality, implemented by a generic piece of hardware (the “threshold adjusting unit” is a “NMOS transistor” or its equivalents, amounts to mere instructions to apply an exception (“(1) Whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished”) as per MPEP 2106.05(f); specifically, without any implementation details of the neural network, the generically recited spiking neural network does not significantly limit the practice of the subsequent claimed limitations which were shown above to recite an abstract idea
Step 2B:
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional element is:
“A spiking neural network comprising a plurality of neurons … wherein each neuron comprises: a threshold adjusting unit”; this does not amount to significantly more than the judicial exception, for the reasons recited above in Step 2A Prong 2
Dependent Claims:
Claim 11 recites:
“accumulating an input signal by time-integrating”; integrating values together over time, whether that be through concatenation, addition, or some other method, is an evaluation that can be performed by a human with pen and paper, and is thus a mental process or mathematical concept
“firing an output signal when the accumulated input signal of the accumulation unit exceeds a threshold”; determining when a threshold is exceeded is a mental process; furthermore, “fires to generate a spike” could merely refer to performing a calculation or evaluation when the threshold exceeded, which is also a mental process
“wherein each neuron comprises: a processor coupled to a memory storing instructions to permit the processor to function as: an accumulation unit … a firing unit”; these limitations amount to nothing more than an instruction to apply the abstract idea using a generic computer as per MPEP 2106.05(f) as per MPEP 2106.05(f) under Steps 2A Prong 2 and 2B
Claim 12 recites:
“wherein each neuron, after firing a first output spike, fires subsequent output spikes when accumulated input signals in the accumulation unit exceed the target threshold”; determining when a threshold is exceeded is a mental process; furthermore, “fires to generate a spike” could merely refer to performing a calculation or evaluation when the threshold exceeded, which is also a mental process
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.
Claims 1 and 3-12 are rejected under 35 U.S.C. 103 as being unpatentable over Querlioz et al. (“Immunity to Device Variations in a Spiking Neural Network With Memristive Nanodevices”; hereinafter “Querlioz”) in view of Kesari et al. (“Enabling Homeostasis using Temporal Decay Mechanisms in Spiking CNNs Trained with Unsupervised Spike Timing Dependent Plasticity”, conference end 24 July 2020; hereinafter “Kesari”)
As per Claim 1, Querlioz teaches a method for compensating a difference and/or a variation of a neuron threshold for a firing in a spiking neural network, the method comprising (Querlioz, Page 293 Section III B: “We now study the impact of the variability of the CMOS neurons. The impact of the variability of their threshold is seen in Fig. 10. We can see that without homeostasis the impact of the variability is dramatic. The more excitable neurons (the ones with lower thresholds) spike predominantly and the other neurons do not specialize efficiently. In a typical simulation with a threshold variation of 25%, the most excitable neuron spikes 51% of the time, and in a simulation with a threshold variation of 50%, it spikes 91% of the time. Homeostasis, however, fully compensates this issue (all the neurons spike between 1.5 and 3% of the time, most neurons spiking around 2%). And the same recognition rate as without threshold variation is achieved as evidenced in Fig. 10. Homeostasis appears as particularly valuable in this application. This also stresses the importance to evaluate the robustness of the system not only to nanodevices’ variations, but also to the CMOS’.”
Examiner notes that here, Querlioz teaches that their method of “homeostasis” is effective to “fully compensate” the issue of “variability of the CMOS neurons”).
adjusting an effective threshold for a next firing after a firing of each neuron (Querlioz, Page 291 Section II B 3: “3) Homeostasis: A final issue for the architecture is the adjustment of the neurons’ threshold … Regularly, the threshold of the neuron is increased if the average activity of the neuron is above the target, and decreased if it is below.”
Here, Querlioz teaches that the threshold is adjusted after firing (“activity of the neuron”) for a next firing (“activity of the neuron”)).
wherein adjusting an effective threshold of each neuron comprises lowering a membrane potential of each neuron by an amount of the [target] threshold after the firing of each neuron (Querlioz, Page 291 Section II B 1: “We call X the state variable (a current or a voltage, equivalent of the biological “membrane potential”) of the neuron (expressed in normalized unit where the maximum value of the state variable X is 1). Neurons are leaky integrate-and-fire type … The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”
Here, Querlioz teaches that the “membrane potential” is lowered by the full amount of the threshold (“reset to zero”) after the firing of a neuron (“declares a spike”)).
wherein an amount of charging potential for a next spike generation equals to the [target] threshold (Querlioz, Page 291 Section II B 1: “We call X the state variable (a current or a voltage, equivalent of the biological “membrane potential”) of the neuron (expressed in normalized unit where the maximum value of the state variable X is 1). Neurons are leaky integrate-and-fire type … The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”
Here, Querlioz teaches that the “threshold” is the “membrane potential” at which a spike is generated.)
However, Querlioz does not teach to be the same as a target threshold in each neuron; lowering a membrane potential of each neuron by an amount of the target threshold after the firing of each neuron
Kesari teaches to be the same as a target threshold in each neuron; lowering a membrane potential of each neuron by an amount of the target threshold after the firing of each neuron (Kesari, Page 4 Section III B: “A widely adopted homeostasis enabling method in fully connected SNNs is adaptive threshold, wherein the neuron’s threshold is increased based on its activity. This enables other neurons learn a receptive field that is different. In spiking CNNs, the adaptive threshold is defined per activation map, with all neurons in an activation map bearing the same threshold [14]. As the threshold of the activation map is dictated by its activity, the threshold value at any time instant is indicative of its past activity.”
Here, Kesari teaches a same target threshold in each neuron, in that the “target threshold” is one that equals the thresholds of all the others in the activation map. Furthermore, if all neurons have the same target threshold, then when they are reset to zero (as taught above by Querlioz), then their potentials are all lowered by the amount of the target threshold.)
Kesari is analogous art because it is in the field of endeavor of homeostasis in spiking neural networks. It would have been obvious before the effective filing date of the claimed invention to combine the spiking neural network of Querlioz with the common target threshold for an activation map of Kesari. One of ordinary skill in the art would have been motivated to do so in order to achieve homeostasis and balance neuronal activity, which is similar to the goal of Querlioz above (Kesari, End of Page 6 to Page 7: “First, we quantitatively show that the offset and weight decay mechanisms, coupled with adaptive threshold, lead to homeostatic behavior. In order to do so, we fit a Gaussian distribution to the thresholds across the maps. We observe that by modulating the weights and offset decay constants, we are able to obtain a desired amount of homeostasis.”)
As per Claim 3, the combination of Querlioz and Kesari teaches the method of claim 1 as well as target threshold (see Kesari in rejection to claim 1). Querlioz teaches a neural network is implemented in a hardware (Querlioz, Page 2 Section II: “We first introduce the architecture that we propose for our classifier system. The CMOS input and output “neurons” are connected by the nanodevices that act as synapses.”)
wherein the target threshold is lower than a designed threshold of a neuron (Querlioz, Page 4 Right Column: “Regularly, the threshold of the neuron is increased if the average activity of the neuron is above the target, and decreased if it is below.” Here, the target threshold is lower, so the effective threshold must be decreased.)
As per Claim 4, the combination of Querlioz and Kesari teaches the method of claim 1 as well as target threshold (see Kesari in rejection to claim 1). Querlioz teaches wherein an effective threshold for a second and all subsequent firings is set equal to the target threshold. (Querlioz, Page 291 Section II B 3: “3) Homeostasis: A final issue for the architecture is the adjustment of the neurons’ threshold … Regularly, the threshold of the neuron is increased if the average activity of the neuron is above the target, and decreased if it is below.” Here, Querlioz teaches that the threshold is adjusted until activity reaches a homeostatic target, and Examiner notes that in this case when the activity reaches the homeostatic target, the threshold will be effective for subsequent firings.)
As per Claim 5, the combination of Querlioz and Kesari teaches the method of claim 1 as well as target threshold (see Kesari in rejection to claim 1). Querlioz teaches wherein the target threshold is adjusted to be less than a real threshold of the each neuron. (Querlioz, Page 4 Right Column: “Regularly, the threshold of the neuron is increased if the average activity of the neuron is above the target, and decreased if it is below.” Here, the target threshold is lower, so the effective threshold must be decreased.)
As per Claim 6, Querlioz teaches a method for discharging a membrane potential after a firing of a neuron in a spiking neural network, the method comprising (Querlioz, Page 291 Section II B 1: “The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”)
discharging a [same] amount of a membrane potential for each neuron after the firing (Querlioz, Page 291 Section II B 1: “The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”)
wherein discharging the same amount of a membrane potential for each neuron after the firing is discharging an amount of a [target] threshold for each neuron after the firing (Querlioz, Page 291 Section II B 1: “We call X the state variable (a current or a voltage, equivalent of the biological “membrane potential”) of the neuron (expressed in normalized unit where the maximum value of the state variable X is 1). Neurons are leaky integrate-and-fire type … The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”
Here, Querlioz teaches that the “membrane potential” is lowered by the full amount of the threshold (“reset to zero”) after the firing of a neuron (“declares a spike”)).
wherein an amount of charging potential for a next spike generation equals to the [target] threshold (Querlioz, Page 291 Section II B 1: “We call X the state variable (a current or a voltage, equivalent of the biological “membrane potential”) of the neuron (expressed in normalized unit where the maximum value of the state variable X is 1). Neurons are leaky integrate-and-fire type … The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”
Here, Querlioz teaches that the “threshold” is the “membrane potential” at which a spike is generated.)
However, Querlioz does not teach discharging a same amount of a membrane potential; discharging an amount of a target threshold
Kesari teaches discharging a same amount of a membrane potential; discharging an amount of a target threshold (Kesari, Page 4 Section III B: “A widely adopted homeostasis enabling method in fully connected SNNs is adaptive threshold, wherein the neuron’s threshold is increased based on its activity. This enables other neurons learn a receptive field that is different. In spiking CNNs, the adaptive threshold is defined per activation map, with all neurons in an activation map bearing the same threshold [14]. As the threshold of the activation map is dictated by its activity, the threshold value at any time instant is indicative of its past activity.”
Here, Kesari teaches a same target threshold in each neuron, in that the “target threshold” is one that equals the thresholds of all the others in the activation map. Furthermore, if all neurons have the same target threshold, then when they are reset to zero (as taught above by Querlioz), then their potentials are all lowered by the amount of the target threshold, and thus they all discharge the same amount of membrane potential.)
Kesari is analogous art because it is in the field of endeavor of homeostasis in spiking neural networks. It would have been obvious before the effective filing date of the claimed invention to combine the spiking neural network of Querlioz with the common target threshold for an activation map of Kesari. One of ordinary skill in the art would have been motivated to do so in order to achieve homeostasis and balance neuronal activity, which is similar to the goal of Querlioz above (Kesari, End of Page 6 to Page 7: “First, we quantitatively show that the offset and weight decay mechanisms, coupled with adaptive threshold, lead to homeostatic behavior. In order to do so, we fit a Gaussian distribution to the thresholds across the maps. We observe that by modulating the weights and offset decay constants, we are able to obtain a desired amount of homeostasis.”)
As per Claim 7, the combination of Querlioz and Kesari teaches the method of claim 6. Querlioz teaches wherein each neuron fires to generate a spike when a membrane potential of a time integration and accumulation of an input signal exceed a threshold. (Querlioz, Page 291 Section II B: “1) Output Neurons’ Dynamics: Exploiting the devices requires connecting them to processing units — silicon neurons able to process and generate spikes in a bioinspired manner by integration of their input. We call X the state variable (a current or a voltage, equivalent of the biological “membrane potential”) of the neuron (expressed in normalized unit where the maximum value of the state variable X is 1). Neurons are leaky integrate-and-fire type, which is meant to solve the simple following equation:
PNG
media_image1.png
46
152
media_image1.png
Greyscale
where τ is a leak time constant, and g and γ are constants … The neuron declares a spike if X reaches a given threshold Xth , in which case X is reset to zero.”)
As per Claim 8, Querlioz teaches a resetting method for a neuron for a next firing after a firing of a neuron in a neural network, the resetting comprising (Querlioz, Page 291 Section II B 1: “The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”)
reducing an amount of accumulated input signals by a [same] amount for each neuron (Querlioz, Page 291 Section II B 1: “The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”)
wherein the reducing the amount of accumulated input signals by the [same] amount for each neuron is reducing an amount of a [target] threshold for each neuron (Querlioz, Page 291 Section II B 1: “We call X the state variable (a current or a voltage, equivalent of the biological “membrane potential”) of the neuron (expressed in normalized unit where the maximum value of the state variable X is 1). Neurons are leaky integrate-and-fire type … The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”
Here, Querlioz teaches that the accumulated input signals (“integrate”, “membrane potential”) is lowered by the full amount of the threshold (“reset to zero”) after the firing of a neuron (“declares a spike”)).
wherein an amount of charging potential for a next spike generation equals to the [target] threshold (Querlioz, Page 291 Section II B 1: “We call X the state variable (a current or a voltage, equivalent of the biological “membrane potential”) of the neuron (expressed in normalized unit where the maximum value of the state variable X is 1). Neurons are leaky integrate-and-fire type … The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”
Here, Querlioz teaches that the “threshold” is the “membrane potential” at which a spike is generated.)
However, Querlioz does not teach reducing an amount of accumulated input signals by a same amount for each neuron; reducing an amount of a target threshold
Kesari teaches reducing an amount of accumulated input signals by a same amount for each neuron; reducing an amount of a target threshold (Kesari, Page 4 Section III B: “A widely adopted homeostasis enabling method in fully connected SNNs is adaptive threshold, wherein the neuron’s threshold is increased based on its activity. This enables other neurons learn a receptive field that is different. In spiking CNNs, the adaptive threshold is defined per activation map, with all neurons in an activation map bearing the same threshold [14]. As the threshold of the activation map is dictated by its activity, the threshold value at any time instant is indicative of its past activity.”
Here, Kesari teaches a same target threshold in each neuron, in that the “target threshold” is one that equals the thresholds of all the others in the activation map. Furthermore, if all neurons have the same target threshold, then when they are reset to zero (as taught above by Querlioz), then their potentials are all lowered by the amount of the target threshold, and thus they all discharge the same amount of accumulated input signals.)
Kesari is analogous art because it is in the field of endeavor of homeostasis in spiking neural networks. It would have been obvious before the effective filing date of the claimed invention to combine the spiking neural network of Querlioz with the common target threshold for an activation map of Kesari. One of ordinary skill in the art would have been motivated to do so in order to achieve homeostasis and balance neuronal activity, which is similar to the goal of Querlioz above (Kesari, End of Page 6 to Page 7: “First, we quantitatively show that the offset and weight decay mechanisms, coupled with adaptive threshold, lead to homeostatic behavior. In order to do so, we fit a Gaussian distribution to the thresholds across the maps. We observe that by modulating the weights and offset decay constants, we are able to obtain a desired amount of homeostasis.”)
As per Claim 9, the combination of Querlioz and Kesari teaches the resetting method of claim 8. Querlioz teaches wherein the accumulated input signals are obtained by time integration of the input signals, and wherein the neuron fires to generate a spike when the accumulated input signals exceed a threshold. (Querlioz, Page 291 Section II B: “1) Output Neurons’ Dynamics: Exploiting the devices requires connecting them to processing units — silicon neurons able to process and generate spikes in a bioinspired manner by integration of their input. We call X the state variable (a current or a voltage, equivalent of the biological “membrane potential”) of the neuron (expressed in normalized unit where the maximum value of the state variable X is 1). Neurons are leaky integrate-and-fire type, which is meant to solve the simple following equation:
PNG
media_image1.png
46
152
media_image1.png
Greyscale
where τ is a leak time constant, and g and γ are constants … The neuron declares a spike if X reaches a given threshold Xth , in which case X is reset to zero.”)
As per Claim 10, Querlioz teaches a spiking neural network comprising a plurality of neurons (Querlioz, Abstract: “We propose a novel neural network-based computing paradigm, which exploits their specific physics, and which has virtual immunity to their variability. Memristive devices are used as synapses in a spiking neural network performing unsupervised learning.”)
wherein the plurality of neurons time-integrate and accumulate an input signal and fire an output spike when the accumulated input signal exceeds a threshold (Querlioz, Page 291 Section II B: “1) Output Neurons’ Dynamics: Exploiting the devices requires connecting them to processing units — silicon neurons able to process and generate spikes in a bioinspired manner by integration of their input. We call X the state variable (a current or a voltage, equivalent of the biological “membrane potential”) of the neuron (expressed in normalized unit where the maximum value of the state variable X is 1). Neurons are leaky integrate-and-fire type, which is meant to solve the simple following equation:
PNG
media_image1.png
46
152
media_image1.png
Greyscale
where τ is a leak time constant, and g and γ are constants … The neuron declares a spike if X reaches a given threshold Xth , in which case X is reset to zero.”)
wherein after firing the spike, an amount of accumulated input signals is reduced by a [same] amount of a [target] threshold for firing a next spike (Querlioz, Page 291 Section II B 1: “The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”)
wherein each neuron comprises: a threshold adjusting unit reducing the amount of the accumulated input signal of the accumulation unit by the amount of a [target] threshold in response to the output spike of the firing unit (Querlioz, Page 291 Section II B 1: “We call X the state variable (a current or a voltage, equivalent of the biological “membrane potential”) of the neuron (expressed in normalized unit where the maximum value of the state variable X is 1). Neurons are leaky integrate-and-fire type … The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”
Here, Querlioz teaches that the accumulated input signals (“integrate”, “membrane potential”) is lowered by the full amount of the threshold (“reset to zero”) after the firing of a neuron (“declares a spike”)).
Querlioz also teaches a threshold adjusting unit (Page 288: “using Complementary Metal–Oxide Semiconductor (CMOS) circuits to model its spiking neurons and synapses.”)
wherein an amount of charging potential for a next spike generation equals to the [target] threshold (Querlioz, Page 291 Section II B 1: “We call X the state variable (a current or a voltage, equivalent of the biological “membrane potential”) of the neuron (expressed in normalized unit where the maximum value of the state variable X is 1). Neurons are leaky integrate-and-fire type … The neuron declares a spike if X reaches a given threshold Xth, in which case X is reset to zero.”
Here, Querlioz teaches that the “threshold” is the “membrane potential” at which a spike is generated.)
However, Querlioz does not teach reduced by a same amount of a target threshold
Kesari teaches reduced by a same amount of a target threshold (Kesari, Page 4 Section III B: “A widely adopted homeostasis enabling method in fully connected SNNs is adaptive threshold, wherein the neuron’s threshold is increased based on its activity. This enables other neurons learn a receptive field that is different. In spiking CNNs, the adaptive threshold is defined per activation map, with all neurons in an activation map bearing the same threshold [14]. As the threshold of the activation map is dictated by its activity, the threshold value at any time instant is indicative of its past activity.”
Here, Kesari teaches a same target threshold in each neuron, in that the “target threshold” is one that equals the thresholds of all the others in the activation map. Furthermore, if all neurons have the same target threshold, then when they are reset to zero (as taught above by Querlioz), then their potentials are all lowered by the amount of the target threshold, and thus they all discharge the same amount of accumulated input signals.)
Kesari is analogous art because it is in the field of endeavor of homeostasis in spiking neural networks. It would have been obvious before the effective filing date of the claimed invention to combine the spiking neural network of Querlioz with the common target threshold for an activation map of Kesari. One of ordinary skill in the art would have been motivated to do so in order to achieve homeostasis and balance neuronal activity, which is similar to the goal of Querlioz above (Kesari, End of Page 6 to Page 7: “First, we quantitatively show that the offset and weight decay mechanisms, coupled with adaptive threshold, lead to homeostatic behavior. In order to do so, we fit a Gaussian distribution to the thresholds across the maps. We observe that by modulating the weights and offset decay constants, we are able to obtain a desired amount of homeostasis.”)
As per Claim 11, the combination of Querlioz and Kesari teaches the spiking neural network of claim 10. Querlioz teaches wherein each neuron comprises: a processor coupled to a memory storing instructions to permit the processor to function as: an accumulation unit accumulating an input signal by time-integrating; and a firing unit firing an output signal when the accumulated input signal of the accumulation unit exceeds a threshold. (Querlioz, Page 291 Section II B: “1) Output Neurons’ Dynamics: Exploiting the devices requires connecting them to processing units — silicon neurons able to process and generate spikes in a bioinspired manner by integration of their input. We call X the state variable (a current or a voltage, equivalent of the biological “membrane potential”) of the neuron (expressed in normalized unit where the maximum value of the state variable X is 1). Neurons are leaky integrate-and-fire type, which is meant to solve the simple following equation:
PNG
media_image1.png
46
152
media_image1.png
Greyscale
where τ is a leak time constant, and g and γ are constants … The neuron declares a spike if X reaches a given threshold Xth , in which case X is reset to zero.”
Querlioz also teaches a processor comprising units in Page 288 Top Right: “using Complementary Metal–Oxide Semiconductor (CMOS) circuits to model its spiking neurons and synapses” and Page 289 Section II: “The CMOS input and output “neurons” are connected by the nanodevices that act as synapses. It is natural to lay out the nanodevices in the widely studied crossbar as illustrated on Fig. 1, where CMOS silicon neurons and their associated synaptic driving circuitry are the dots, the squares being the nanodevices. The synapses indeed act as adaptive resistors.”)
As per Claim 12, the combination of Querlioz and Kesari teaches the spiking neural network of claim 11. Querlioz teaches wherein each neuron, after firing a first output spike, fires subsequent output spikes when accumulated input signals in the accumulation unit exceed the target threshold. (Querlioz, Page 291 Section II B 3: “3) Homeostasis: A final issue for the architecture is the adjustment of the neurons’ threshold … Regularly, the threshold of the neuron is increased if the average activity of the neuron is above the target, and decreased if it is below.” Here, Querlioz teaches that the threshold is adjusted until activity reaches a homeostatic target, and Examiner notes that in this case when the activity reaches the homeostatic target, the threshold will be effective for subsequent firings.)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Chen et al. (US 2019/0197391 A1) discloses in [0020]: “In an example, a neuromorphic computer may implement intrinsic homeostatic control through firing threshold regulation. For example, every neuron has a variable threshold and its value is adjusted in response to the neuron's firing rate. When a neuron is firing rapidly, its firing rate may be reduced by incrementing the threshold at every firing. Similarly, a dormant neuron may be made active by decrementing the threshold each time-step. This approach may require additional state bits for each neuron in order to support variable threshold values for every neuron.
Falez et al. (“Multi-layered Spiking Neural Network with Target Timestamp Threshold Adaptation and STDP”) discloses in Page 4: “This paper introduces a new method to adjust neuron thresholds. The idea is to define an objective timestamp ttarget, and to train neurons to fire at this timestamp. To do so, we define a threshold adaptation rule, as follows:
PNG
media_image2.png
20
318
media_image2.png
Greyscale
with Vth the neuron threshold, t the timestamp at which the neuron fires, ηth the threshold learning rate and Thmin the minimal threshold allowed. This rule corrects the timing error between the actual firing timestamp t and the objective timestamp ttarget at each neuron discharge. The optimal value for ttarget depends on the dataset; it requires an exhaustive search in the range [Tstart, Tend]. This rule assumes that the input spikes that trigger an output spike are not simultaneous, which is the case in practice with image data. With data that does not verify this assumption, synaptic delays would have to be adapted.
Qu et al. (“Efficient and hardware-friendly methods to implement competitive learning for spiking neural networks”) discloses in Page 13481: “The widely used method to achieve homeostasis is based on membrane threshold adaptation. MTA-based homeostasis methods increase the threshold of the excitatory neuron if it spikes too frequently and decrease the threshold if it spikes too rarely.”
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LEONARD A SIEGER whose telephone number is (571)272-9710. The examiner can normally be reached M-F 8:00 am - 5:00 pm.
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, David Yi can be reached at (571) 270-7519. 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.
/LEONARD A SIEGER/Examiner, Art Unit 2126
Prosecution Insights