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 .
Status of the Application
This action is a first action on the merits in response to the application filed on 07/06/2023.
Status of Claims
Claims 1-20 filed on 07/06/2023 are currently pending and have been examined in this application.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 07/06/2023 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless – (a) (1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-20 are rejected under 35 U.S.C. 102 (a) (1) as being Stochastic Neuromorphic Circuits for Solving MAXCUT, Bradley H. Theilman, October 5, 2022 hereinafter Bradley
Regarding claim 1. Bradley teaches A method for solving a discrete optimization problem in a neuromorphic device, the method comprising: connecting a number of random noise generators to a number of leaky integrate and fire (LIF) neurons; assigning weights to the connections between the random noise generators and the LIF neurons, wherein the weights are chosen to produce a correlation matrix determined by the discrete optimization problem; [Bradley, page 4 second paragraph, Bradley teaches “Here Wi is the real-valued connection weight between device α and LIF neuron i. The variable s is the state of device and takes the values {0; 1}” wherein device α is equivalent to random noise generator connected to LIF. Wherein generated weights and figure 1 shows a correlation matrix] integrating, by the LIF neurons, random bits generated by the random noise generators according to the assigned weights to produce specified correlated activity variables; [Bradley, page 4 first column second paragraph, Bradley teaches “Here Wi is the real-valued connection weight between device α and LIF neuron i. The variable s is the state of device and takes the values {0; 1}” wherein the real-valued connection weight between device α and LIF is equivalent to weights to produce specified correlated activity variables] feeding the correlated activity variables to an output LIF neuron that operates according to a plasticity rule; and outputting, by the output LIF neuron, an approximate solution to the discrete optimization problem according to the correlated activity variables [Bradley, page 5 second column first paragraph, Bradley teaches “LIF-Trevisan circuit implementing a stochastic approximation to MAXCUT by combining hardware randomness with anti-Hebbian synaptic plasticity. The connection weights between the random device pool (left) and the LIF neurons are set proportional to the adjacency matrix of the graph. The activity of the LIF neurons drives synaptic plasticity on the weight vector onto an output neuron” wherein operating according to a plasticity rule and outputting].
Regarding claim 2. wherein the random noise generators comprise coin flip devices [Bradley, page 3 second column second paragraph, Bradley teaches “stochastic devices as analogous to “coin flips” such that at any given time, the device can be in one of two states (“heads” or “tails”; “0” or “1”)” wherein coin flip device].
Regarding claim 3. wherein the coin flip devices are unbiased Bernoulli devices [Bradley, page 3 second column second paragraph, Bradley teaches “stochastic devices as analogous to “coin flips” such that at any given time, the device can be in one of two states (“heads” or “tails”; “0” or “1”)” wherein coin flip device at any given time, the device can be in one of two states (“heads” or “tails”; “0” or “1”) is equivalent to unbiased Bernoulli device with specific probability that functions without preference, prejudice, or distortion].
Regarding claim 4. wherein the coin flip devices are biased [Bradley, page 3 second column second paragraph, Bradley teaches “stochastic devices as analogous to “coin flips” such that at any given time, the device can be in one of two states (“heads” or “tails”; “0” or “1”)” wherein coin flip device at any given time, the device can be in one of two states (“heads” or “tails”; “0” or “1”) is equivalent to unbiased device with specific outcome that functions without preference, prejudice, or distortion].
Regarding claim 5. wherein the output LIF neuron operates according to a Hebbian plasticity rule [Bradley, page 4 first column last paragraph, Bradley teaches “As stated, this rule is unstable. Oja presented a modification to this plasticity rule that preserved the Hebbian principle but enforced weight stability [23]. Oja’s rule is given by the formula…” wherein Hebbian plasticity principle].
Regarding claim 6. wherein the weights assigned to the connections between the random noise generators and the LIF neurons are proportional to a number of vectors calculated according to a semidefinite programming (SDP) problem [Bradley, page 3 first column third paragraph, Bradley teaches “The solution of this semidefinite programming problem is a set of unit vectors wi, one for each vertex in the graph” wherein semidefinite programming (SDP) problem].
Regarding claim 7. wherein the number of random noise generators depends on a specified fidelity of sampling [Bradley, page 7 second column last paragraph, Bradley teaches “While the number of samples required suggests a disadvantage, at the speed of hardware, the greater number of samples required will likely be a trivial increase in the running time compared to a software implementation. Current hardware implementations of LIF neurons operate with time constants on the order of 1 nanosecond [7], [12]. Using this value as a reference time step for a hardware implementation of these circuits, the circuits could generate millions of samples in the time required for a software simple spectral computation ( 10ms), or billions of samples in the time required to solve and sample the Goemans-Williams SDP [21].” wherein the hardware depend on the number of samples].
Regarding claim 8. wherein the output LIF neuron operates according to an anti-Hebbian plasticity rule [Bradley, page 4 second column third paragraph, Bradley teaches “By considering anti-Hebbian plasticity, Oja derived a related, stabilized learning rule that converges to the minimum eigenvector of the covariance matrix” wherein anti-Hebbian plasticity rule].
Regarding claim 9. wherein the weights assigned to the connections between the random noise generators and the LIF neurons are proportional to an adjacency matrix [Bradley, page 4 second column fourth paragraph, Bradley teaches “By considering anti-Hebbian plasticity, Oja derived a related, stabilized learning rule that converges to the minimum eigenvector of the covariance matrix” wherein input weights are proportional to an adjacency matrix].
Regarding claim 10. wherein the number of random noise generators equals the number of LIF neurons [Bradley, page 4 first column second paragraph, Bradley teaches “Here Wi is the real-valued connection weight between device and LIF neuron i.” Also see figure 2 where the number of random noise generator is connected to the same number of LIF].
Regarding claim 11, the claim recites analogous limitations to claim 1 above, and is therefore rejected on the same premise. Claim 1 is a method claim while claim 11 is directed to a device which is anticipated by Bradley figure 2.
Regarding claims 12-20, claims 12-20 recite substantially similar limitations as claim 2-10, respectively; therefore, claims 12-20 are rejected with the same rationale, reasoning, and motivation provided above for claims 2-10, respectively. Claims 2-10 are method claims while claims 12-20 are directed to a device which is anticipated by Bradley figure 2.
Conclusion
Any inquiry concerning this communication from the examiner should be directed to Abdallah El-Hagehassan whose contact information is (571) 272-0819 and Abdallah.el-hagehassan@uspto.gov The examiner can normally be reached on Monday- Friday 8 am to 5 pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Rutao Wu can be reached on (571) 272-6045. The fax phone number for the organization where this application or proceeding is assigned is (571) 273-3734.
Information regarding the status of an application may be obtained from the patent application information retrieval (PAIR) system. Status information of published applications may be obtained from either private PAIR or public PAIR. Status information of unpublished applications is available through private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have any questions on access to the private PAIR system, contact the electronic business center (EBC) at (866) 271-9197 (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 US or Canada) or (571) 272-1000.
/ABDALLAH A EL-HAGE HASSAN/
Primary Examiner, Art Unit 3623