DETAILED ACTION
This action is responsive to claims filed on 16 November 2023.
Claims 1-5 are pending for examination.
Allowable Subject Matter
Claim 1 would be allowable if rewritten or amended to overcome the rejection under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 2nd paragraph, set forth in this Office Action.
Claims 2-5, which depend directly or indirectly from Claim 1, would be allowable.
The following is a statement of reasons for the indication of allowable subject matter.
The prior art, made of record, does not teach, make obvious, or suggest the claim limitations of Claim 1 required elements, as disclosed in Applicant’s claims. Specifically, the limitations directed to
“step 3: sample generation: performing non-overlapping window sliding on processed differential entropy features at T time windows, and performing the operation on each channel at each frequency band, to obtain time*channel*frequency band; converting a one-dimensional channel data sequence into a two-dimensional mesh matrix sequence, wherein a position correspondence is obtained through a two-dimensional topology map of an EEG electrode cap; and finally obtaining an input sample: time*H*W*frequency band, wherein H and W are a height and a width of the two-dimensional mesh matrix sequence”,
“step 4: defining an input and an output of a model, wherein an input of single training of the model comprises a batch of samples, a structure of each sample is time*H*W*frequency band, and thus an input structure Input of the model is batch*time*H*W*frequency band; and an output of the model is a batch of vectors in a form of one-hot, and an output structure Output=batch*classes, wherein classes represent a probability that the sample belongs to the class, which is represented by using a decimal 0 to 1, and batch represents a quantity of batches”,
“step 5: defining a spiking neuron, wherein a leaky-integrate-fire (LIF) model is used as a neuron model; and the LIF model is a spiking neural network combining a conventional CNN, a fully connected network, and a spiking neuron mechanism, and performs, by using a modified activation function and an activation function of an activation model of the spiking neuron with help of a surrogate gradient function, input and output between layers in the activation mode in a network training process, and also sequentially performs spiking output, activation, and transmission on an intra-layer time slice”,
“step 6: defining a spiking neural network architecture, wherein 12 a spiking neural network structure comprises an adaptive spiking convolutional encoder, a spiking convolutional feature extraction network, and a spiking fully connected classifier”
in exemplary Claim 1 limitations.
The closest prior arts, listed below, discloses:
Xing et al. (NPL: “Deep Spiking Neural Networks with Applications to Human Gesture Recognition”) teaches a SNN-based event-driven hand gesture recognition system, shown to be effective in an experiment on hand gesture recognition with its spiking recurrent convolutional neural network (SCRNN) design, which combines both designed convolution operation and recurrent connectivity to maintain spatial and temporal relations with address-event representation (AER) data.
Chen et al. (NPL: “Emotion recognition from spatiotemporal EEG representations with hybrid convolutional recurrent neural networks via wearable multi-channel headset”) teaches data representation of electroencephalogram (EEG), which transforms 1D chain-like EEG vector sequences into 2D mesh-like matrix sequences.
Kumar et al. (NPL: “Decoding EEG With Spiking Neural Networks on Neuromorphic Hardware”) teaches an SNN architecture with an input encoding and network design that exploits the priors of spatial and temporal dependencies in the EEG signal, comprised of spatial convolutional, temporal convolutional, and recurrent layers.
Tan et al. (NPL: “NeuroSense: Short-term emotion recognition and understanding based on spiking neural network modelling of spatio-temporal EEG patterns”) teaches a short-term emotion recognition framework based on spiking neural network (SNN) modelling of spatio-temporal EEG patterns.
Luo et al. (NPL: “EEG-Based Emotion Classification Using Spiking Neural Networks”) teaches a method of using the spiking neural networks (SNNs) and the electroencephalograph (EEG) processing techniques to recognize emotion states.
In summary, the references made of record, fail to disclose the required claimed technical features recited by the Claim 1 limitations as a whole.
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 .
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-5 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites “time*channel*frequency band”, “time*H*W*frequency band”, “time*H*W*frequency band”, “batch*time*H*W*frequency band”, “Output=batch*classes” in lines 15, 18, 21, 22, 23, respectively. It is indefinite as to whether the * in claim limitations denote a multiplication operation between listed elements or elements arranged within a structure. For examination purposes, * between elements in claim limitations has been construed to denote any arrangement of the listed elements within a structure. Claims 2-5, which depend directly or indirectly from claim 1, are similarly rejected.
Claim 3 recites “64*9*9”, “64*6*6”, “64*6*6” in lines 48, 48, 54, respectively. It is indefinite as to whether the * in claim limitations denote a multiplication operation between listed elements or elements arranged within a structure. For examination purposes, * between elements in claim limitations has been construed to denote any arrangement of the listed elements within a structure. Claim 5, which depends directly from claim 3, is similarly rejected.
Claim 4 recites “16*32*9*9*4”, “32*16*9*9*4”, in lines 4, 4, respectively. It is indefinite as to whether the * in claim limitations denote a multiplication operation between listed elements or elements arranged within a structure. For examination purposes, * between elements in claim limitations has been construed to denote any arrangement of the listed elements within a structure.
Claim 5 recites “16*32*9*9*4”, “32*16*9*9*4”, in lines 4, 4, respectively. It is indefinite as to whether the * in claim limitations denote a multiplication operation between listed elements or elements arranged within a structure. For examination purposes, * between elements in claim limitations has been construed to denote any arrangement of the listed elements within a structure.
The terms “obviously” and “extremely” in lines 24 and 25, respectively, of Claim 2, are relative terms which renders the claim indefinite. The terms “obviously” and “extremely” are not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. For examination purposes, "obviously causes network training to be extremely unstable" has been construed to be “directly causes network training to be unstable to a greater degree”.
Claim 1 recites the limitation "the operation" in line 14. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the operation" has been construed to be “an operation”. Claims 2-5, which depend directly or indirectly from claim 1, are similarly rejected.
Claim 1 recites the limitation "input structure Input" in line 22. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "input structure Input" has been construed to be “input structure”. Claims 2-5, which depend directly or indirectly from claim 1, are similarly rejected.
Claim 1 recites the limitation "the class" in line 24. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the class" has been construed to be “a class”. Claims 2-5, which depend directly or indirectly from claim 1, are similarly rejected.
Claim 1 recites the limitation "the spiking neuron" in line 30. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the spiking neuron" has been construed to be “the spiking neuron mechanism”. Claims 2-5, which depend directly or indirectly from claim 1, are similarly rejected.
Claim 1 recites the limitation "the activation mode" in line 31. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the activation mode" has been construed to be “the activation model”. Claims 2-5, which depend directly or indirectly from claim 1, are similarly rejected.
Claim 1 recites the limitation "the spiking neural network" in line 36-37. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the spiking neural network" has been construed to be “the spiking neural network structure”. Claims 2-5, which depend directly or indirectly from claim 1, are similarly rejected.
Claim 1 recites the limitation "the spiking neural network" in line 38. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the spiking neural network" has been construed to be “the spiking neural network structure”. Claims 2-5, which depend directly or indirectly from claim 1, are similarly rejected.
Claim 1 recites the limitation "the input structure defined in step 3" in line 38-39. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the input structure defined in step 3" has been construed to be “the input structure defined in step 4”. Claims 2-5, which depend directly or indirectly from claim 1, are similarly rejected.
Claim 1 recites the limitation "the network" in line 40. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the network" has been construed to be “the spiking neural network structure”. Claims 2-5, which depend directly or indirectly from claim 1, are similarly rejected.
Claim 1 recites the limitation "the spiking neural network" in line 42. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the spiking neural network" has been construed to be “the spiking neural network structure”. Claims 2-5, which depend directly or indirectly from claim 1, are similarly rejected.
Claim 2 recites the limitation "the formula" in line 10. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the formula" has been construed to be “the formula (4)”. Claims 3-5, which depend directly or indirectly from claim 2, are similarly rejected.
Claim 2 recites the limitation "the model" in line 11. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the model" has been construed to be “the used neuron model”. Claims 3-5, which depend directly or indirectly from claim 2, are similarly rejected.
Claim 2 recites the limitation "the spiking neuron output" in line 21. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the spiking neuron output" has been construed to be “a spiking neuron output”. Claims 3-5, which depend directly or indirectly from claim 2, are similarly rejected.
Claim 2 recites the limitation "the directly trained spiking neural network" in line 25-26. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the directly trained spiking neural network" has been construed to be “the directly trained spiking neural network architecture”. Claims 3-5, which depend directly or indirectly from claim 2, are similarly rejected.
Claim 3 recites the limitation "the model" in line 3. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the model" has been construed to be “the LIF model”. Claim 5, which depends directly from claim 3, is similarly rejected.
Claim 3 recites the limitation "the model" in line 4. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the model" has been construed to be “the LIF model”. Claim 5, which depends directly from claim 3, is similarly rejected.
Claim 3 recites the limitation "the network" in line 8-9. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the network" has been construed to be “the spiking convolutional neural network”. Claim 5, which depends directly from claim 3, is similarly rejected.
Claim 3 recites the limitation "the LIF neural activation layer" in line 21. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the LIF neural activation layer" has been construed to be “the LIF neuron activation layer”. Claim 5, which depends directly from claim 3, is similarly rejected.
Claim 4 recites the limitation "the spiking convolutional layer and the spiking fully connected layer in step 6" in line 2-3. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the spiking convolutional layer and the spiking fully connected layer in step 6" has been construed to be “a spiking convolutional layer and a spiking fully connected layer in step 6”.
Claim 4 recites the limitation "the spiking neural network" in line 4-5. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the spiking neural network" has been construed to be “the spiking neural network architecture”.
Claim 4 recites the limitation "the LIF neuron" in line 7. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the LIF neuron" has been construed to be “the LIF neuron node”.
Claim 4 recites the limitation "the formula" in line 10. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the formula" has been construed to be “the formula (1)”.
Claim 4 recites the limitation "the process" in line 13. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the process" has been construed to be “the training process”.
Claim 5 recites the limitation "the spiking convolutional layer and the spiking fully connected layer in step 6" in line 2-3. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the spiking convolutional layer and the spiking fully connected layer in step 6" has been construed to be “a spiking convolutional layer and a spiking fully connected layer in step 6”.
Claim 5 recites the limitation "the spiking neural network" in line 4-5. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the spiking neural network" has been construed to be “the spiking neural network architecture”.
Claim 5 recites the limitation "the LIF neuron" in line 7. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the LIF neuron" has been construed to be “the LIF neuron node”.
Claim 5 recites the limitation "the formula" in line 10. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the formula" has been construed to be “the formula (1)”.
Claim 5 recites the limitation "the process" in line 13. There is insufficient antecedent basis for this limitation in the claim. For examination purposes, "the process" has been construed to be “the training process”.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MAGGIE MAIDO whose telephone number is (703) 756-1953. The examiner can normally be reached M-Th: 6am - 4pm.
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, Michael Huntley can be reached on (303) 297-4307. 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.
/MM/Examiner, Art Unit 2129
/MICHAEL J HUNTLEY/Supervisory Patent Examiner, Art Unit 2129
Prosecution Insights