IP Library › Granted Patent US 12,380,320
Granted Patent B2
US 12,380,320 · App. 17/294,697 · Granted Aug 5, 2025

Resilient neural network

Inventors: Amir Zjajo (The Hague, NL); Sumeet Susheel Kumar (The Hague, NL)
Assignee: INNATERA NANOSYSTEMS B.V.
G06N3/049G06N3/045G06N3/063G06N3/08
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,380,320
App. No.
17/294,697
Granted
Aug 5, 2025
Kind
B2
Abstract

The present invention discloses a spiking neural network for classifying input signals. The spiking neural network comprises a plurality of spiking neurons, and a plurality of synaptic elements interconnecting the spiking neurons to form the network. Each synaptic element is adapted to receive a synaptic input signal and apply a weight to the synaptic input signal to generate a synaptic output signal, the synaptic elements being configurable to adjust the weight applied by each synaptic element. Furthermore, each of the spiking neurons is adapted to receive one or more of the synaptic output signals from one or more of the synaptic elements, and generate a spatio-temporal spike train output signal in response to the received one or more synaptic output signals. The spiking neural network is partitioned into multiple sub-networks, wherein each sub-network comprises a sub-set of the spiking neurons connected to receive synaptic output signals from a sub-set of the synaptic elements. The sub-network is adapted to generate a sub-network output pattern signal in response to a sub-network input pattern signal applied to the sub-network. Furthermore, each sub-network forms part of one or multiple cores in an array of cores, each core consisting of a programmable network of spiking neurons implemented in hardware or a combination of hardware and software. Communication between cores in the core array is arranged through a programmable interconnect structure.

Claims (41)

1. A spiking neural network for classifying input signals, comprising a plurality of spiking neurons implemented in hardware or a combination of hardware and software, and a plurality of synaptic elements interconnecting the spiking neurons to form the network,

wherein each synaptic element is adapted to receive a synaptic input signal and apply a weight to the synaptic input signal to generate a synaptic output signal, the synaptic elements being configurable to adjust the weight applied by each synaptic element,

wherein each of the spiking neurons is adapted to receive one or more of the synaptic output signals from one or more of the synaptic elements, and generate a spatio-temporal spike train output signal in response to the received one or more synaptic output signals,

wherein the weights of the synaptic elements are bounded by bound values, wherein the bound values are stochastic values;

wherein the weight of a synaptic element connected into a spiking neuron i is bounded by bounding the synaptic drive Γ i of the spiking neuron i in the spiking neural network, wherein the synaptic drive Γ i of one of the spiking neuron i is a time-dependent function describing a total transfer function of all synaptic elements that are connected into the neuron; and

wherein the variance of each of the synaptic drives Γ i ; lies below a predetermined value such that the synaptic drive Γ i , of each of the neuron i in the spiking neural network is bound around an equilibrium point Γ i of the synaptic drive Γ i , where noise effects are minimal.

2. The spiking neural network of claim 1 , wherein the weights of the synaptic elements are configured using stochastic weight updates.

3. The spiking neural network of claim 2 , wherein every synapse assembles the activation statistics of its input, the presynaptic neuron, if its output, the postsynaptic neuron, fires, wherein the activation statistics are collected at runtime from samples of an input distribution.

4. The spiking neural network of claim 3 , wherein the weights are updated according to a spike-event triggered stochastic online learning rule given by:

w ij new =w ij +η ij z i ( y i e −w ij −1)

wherein w ij is the old weight of a synapse from input neuron i to output neuron j of the spiking neural network, η ij a local learning rate, y i the input of the presynaptic input neuron i, and z i output at the spiking times of neuron i.

5. The spiking neural network of claim 3 , wherein the random variables used to set the stochastic weight updates in the spiking neural network are independent and identically distributed.

6. The spiking neural network of claim 1 , wherein the variance is adjustable by obtaining an expression for the variance of each of the synaptic drives Γ i , the expression for the variance depending on a control parameter, and wherein the variance of each of the synaptic drives Γ i is adjustable by adjusting the control parameter.

7. The spiking neural network of claim 6 , wherein the synaptic drive Γ i of the spiking neuron i in the spiking neural network can be written in vector form for all neurons in the spiking neural network as Γ=(Γ 1 , . . . , Γ n ) T , wherein n is the number of neurons in the spiking neural network, and wherein Γ satisfies the formula:

dΓ=N (Γ( t )) dt +σ(Γ( t )) d ω( t ),

where N(Γ(t)) is a nominal matrix part and σ(Γ) is a state-dependent noise matrix for the Gaussian white noise process dω(t), where ω is a Wiener process which describes noise in the spiking neural network,

wherein the expression for dr is rewritable in terms of the variance-covariance matrix K(t) of Γ(t) satisfying the following continuous-time algebraic Lyapunov equation:

N (Γ( t )) K ( t )+ K ( t )[ N (Γ( t ))] T +σ(Γ( t ))[σ(Γ( t ))] T =0,

wherein the step of obtaining an expression for the variance of each of the synaptic drives Γ i comprises determining the diagonal values of the variance-covariance matrix K(t).

8. The spiking neural network of claim 1 , wherein the spiking neural network is in a particular core of a core array in a multicore solution, each core consisting of a programmable network of spiking neurons implemented in hardware or a combination of hardware and software, and wherein communication between cores in the core array is arranged through a programmable interconnect structure.

9. The spiking neural network of claim 1 , wherein the spiking neural network is a sub-network of a partitioning of a larger spiking neural network into multiple sub-networks, wherein each sub-network comprises a sub-set of the spiking neurons connected to receive synaptic output signals from a sub-set of the synaptic elements, wherein the sub-network is adapted to generate a sub-network output pattern signal in response to a sub-network input pattern signal applied to the sub-network, wherein each sub-network forms part of one or multiple cores in an array of cores, each core consisting of a programmable network of spiking neurons implemented in hardware or a combination of hardware and software, and wherein communication between cores in the core array is arranged through a programmable interconnect structure.

10. An integrated circuit comprising the spiking neural network of claim 1 .

11. A method for configuring a spiking neural network to diminish noise effects in the spiking neural network,

wherein the spiking neural network comprises a plurality of spiking neurons implemented in hardware or a combination of hardware and software, and a plurality of synaptic elements interconnecting the spiking neurons to form the network,

wherein each synaptic element is adapted to receive a synaptic input signal and apply a weight to the synaptic input signal to generate a synaptic output signal, the synaptic elements being configurable to adjust the weight applied by each synaptic element,

wherein each of the spiking neurons is adapted to receive one or more of the synaptic output signals from one or more of the synaptic elements, and generate a spatio-temporal spike train output signal in response to the received one or more synaptic output signals, the method comprising:

bounding the weights of the synaptic elements by bound values, wherein the bound values are stochastic values;

wherein the weight of a synaptic element connected into a spiking neuron i is bounded by bounding the synaptic drive Γ i of the spiking neuron i in the spiking neural network, wherein the synaptic drive Γ i of one of the spiking neuron i is a time-dependent function describing a total transfer function of all synaptic elements that are connected into the neuron;

wherein the variance of each of the synaptic drives Γ i lies below a predetermined value such that the synaptic drive Γ i of each of the neuron i in the spiking neural network is bound around an equilibrium point Γ* i of the synaptic drive Γ i where noise effects are minimal.

12. The method of claim 11 , wherein the weights of the synaptic elements are configured using stochastic weight updates, wherein every synapse assembles the activation statistics of its input, the presynaptic neuron, if its output, the postsynaptic neuron, fires, wherein the activation statistics are collected at runtime from samples of an input distribution, and wherein the random variables used to set the stochastic weight updates in the spiking neural network are independent and identically distributed.

13. The method of claim 12 , wherein the weights are updated according to a spike-event triggered stochastic online learning rule given by:

w ij new =w ij +η ij z i ( y i e −w ij −1)

wherein w ij is the old weight of a synapse from input neuron i to output neuron j of the spiking neural network, η ij a local learning rate, y i the input of the presynaptic input neuron i, and z i output at the spiking times of neuron i.

14. The method of claim 11 , wherein the variance is adjustable by obtaining an expression for the variance of each of the synaptic drives Γ i , the expression for the variance depending on a control parameter, and wherein the variance of each of the synaptic drives Γ i is adjustable by adjusting the control parameter.

15. The method of claim 14 , wherein the synaptic drive Γ i of the spiking neuron i in the spiking neural network can be written in vector form for all neurons in the spiking neural network as Γ=(Γ 1 , . . . , Γ n ) T , wherein n is the number of neurons in the spiking neural network, and wherein Γ satisfies the formula:

dω=N (Γ( t )) dt +σ(Γ( t )) d ω( t ),

where N(Γ(t)) is a nominal matrix part and σ(Γ) is a state-dependent noise matrix for the Gaussian white noise process dω(t), where ω is a Wiener process which describes noise in the spiking neural network,

wherein the expression for dr is rewritable in terms of the variance-covariance matrix K(t) of Γ(t) satisfying the following continuous-time algebraic Lyapunov equation:

N (Γ( t )) K ( t )+ K ( t )[ N (Γ( t ))] T +σ(Γ( t ))[σ(Γ( t ))] T =0,

wherein the step of obtaining an expression for the variance of each of the synaptic drives Γ i comprises determining the diagonal values of the variance-covariance matrix K(t).

16. The method of claim 15 , wherein the equilibrium point Γ* i of the synaptic drive Γ i can be written in vector form for all neurons in the spiking neural network as Γ*=(Γ* 1 , . . . , Γ* n ) T , for which the noise matrix σ is zero, i.e. σ(Γ*)=0.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 23, 2022
From: ZJAJO, AMIR; KUMAR, SUMEET SUSHEEL
To: INNATERA NANOSYSTEMS B.V.
Reel/Frame 060285/0314 →
Continuity (2)
Provisional Application 62768927 · Nov 18, 2018
Related Publication 20220012564A1 · Jan 13, 2022
References Cited (107)
US 5255347A · Matsuba et al. · 1993 [cited by applicant]
US 9189730B1 · Coenen · 2015 [cited by examiner]
US 9558443B2 · Alvarez-Icaza · 2017 [cited by examiner]
US 11423312B2 · Choi · 2022 [cited by examiner]
US 20130073491A1 · Izhikevich et al. · 2013 [cited by applicant]
US 20130073499A1 · Izhikevich et al. · 2013 [cited by applicant]
US 20140064609A1 · Petre · 2014 [cited by applicant]
US 20150106316A1 · Birdwell · 2015 [cited by examiner]
US 20150242745A1 · Wang et al. · 2015 [cited by applicant]
US 20150346302A1 · Hart · 2015 [cited by examiner]
US 20170116513A1 · Andreopoulos · 2017 [cited by examiner]
US 20170154259A1 · Burr et al. · 2017 [cited by applicant]
US 20170236027A1 · van der Made et al. · 2017 [cited by applicant]
US 20170316310A1 · Cho et al. · 2017 [cited by applicant]
US 20180082182A1 · Amir et al. · 2018 [cited by applicant]
US 20180322384A1 · Augustine · 2018 [cited by examiner]
US 20200272883A1 · Cao · 2020 [cited by examiner]
CN 104641385A · 2015 [cited by applicant]
CN 105122278A · 2015 [cited by applicant]
CN 106022469A · 2016 [cited by applicant]
CN 107092959A · 2017 [cited by applicant]
CN 107408222A · 2017 [cited by applicant]
JP H047660A · 1992 [cited by applicant]
JP 2017509978A · 2017 [cited by applicant]
WO 2015127110A2 · 2015 [cited by applicant]
Galtier, Mathieu, et al. “A biological gradient descent for prediction through a combination of STDP and homeostatic plasticity.” arXiv preprint arXiv:1206.4812 (2012), pp. 1-36 (Year: 2012). [cited by examiner]
Hui, Qing, et al. “A stochastic mean field model for an excitatory and inhibitory synaptic drive cortical neuronal network.” IEEE transactions on neural networks and learning systems 25.4 (2013): pp. 751-763 (Year: 2013… [cited by examiner]
Alawad, Mohammed, et al. “Energy efficient stochastic-based deep spiking neural networks for sparse datasets.” 2017 IEEE International Conference on Big Data (Big Data). IEEE, 2017, p. 311-318. (Year: 2017). [cited by examiner]
Kim, Christopher, et al. “Learning recurrent dynamics in spiking networks.” arXiv preprint arXiv:1803.06622 (Aug. 18, 2018), pp. 1-13 (Year: 2018). [cited by examiner]
Lee, Chankyu, et al. “Deep spiking convolutional neural network trained with unsupervised spike-timing-dependent plasticity.” IEEE Transactions on Cognitive and Developmental Systems 11.3 (May 4, 2018), pp. 384-394 (Yea… [cited by examiner]
Rui, Wang et al. “Research Progress on Photonic Neuromorphic Computing.” 2016. (Year: 2016). [cited by examiner]
Joshi Siddharth et al: “Neuromorphic Event-Driven Multi-Scale Synaptic Connectivity and Plasticity”, 2017 51st Asilomar Conference on Signals, Systems, and computers, IEEE, Oct. 29, 2017. [cited by applicant]
International Search Report for PCT/EP2019/081662 issued on Jun. 24, 2020. [cited by applicant]
International Preliminary Report on Patentability for PCT/EP2019/081662 issued on May 27, 2021. [cited by applicant]
L. Deng, et al. “Recent advances in deep learning for speech research at Microsoft,” IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1-5, 2013. [cited by applicant]
A. Krizhevsky, I. Sutskever, G.E. Hinton, “ImageNet classification with deep convolutional neural networks,” Advances in Neural Information Processing Systems, vol. 25, No. 2, pp. 1-9, 2012. [cited by applicant]
Y.-H. Chen, T. Krishna, J. Erner, V. Sze, “An energy-efficient reconfigurable accelerator for deep convolution al neural networks,” IEEE International Solid-State Circuit Conference, pp. 262-263, 2016. [cited by applicant]
S.W. Park, J. Park, K. bong, D. Shin, J. Lee, S. Choi, H.J. Yoo, “An energy-efficient and scalable deep learning/inference processor with tetra-parallel MIMD architecture for big data applications,” IEEE Transactions on… [cited by applicant]
J. Hasler, B . Marr, “Finding a roadmap to achieve large neuromorphic hardware systems,” Frontiers in Neuroscience, vol. 7, pp. 1-29, 2013. [cited by applicant]
P. O'Connor, D. Neil, S.-C. Liu, T. Delbruck, M. Pfeiffer, “Real-time classification and sensor fusion with a spiking deep belief network,” Frontiers in Neuromorphic Engineering, vol. 7, pp. 1-13, 2013. [cited by applicant]
P. U. Diehl, et al., “Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing,” IEEE International Joint Conference on Neural Networks, pp. 2933-2940, 2015. [cited by applicant]
M.J.M. Pelgrom, A.C.J. Duinmaijer, A.P.G. Welbers, “Matching properties of MOS transistors,” IEEE Journal of Solid-State Circuits, vol. 24, No. 5, pp. 1433-1439, 1989. [cited by applicant]
K.L. Shepard, V. Narayanan, “Noise in deep submicron digital design,” IEEE International Conference on Computer-Aided Design, pp. 524-531, 1997. [cited by applicant]
D. Cohen, M. Nicolelis, “Reduction of single-neuron firing uncertainty by cortical ensembles during motor skill learning,” Journal of Neuroscience, vol. 24, No. 14, pp. 3574-3582, 2004. [cited by applicant]
M. Laubach, J. Wessber, M.A. Nicolelis, “Cortical ensemble activity increasingly predicts behaviour outcomes during learning of a motor task,” Nature, vol. 405, pp. 567-571, 2000. [cited by applicant]
B.V. Dasarathy, B.V. Sheela, “Composite classifier system design: concepts and methodology,” Proceedings of the IEEE, vol. 67, No. 5, pp. 708-713, 1979. [cited by applicant]
L.K. Hansen, P. Salamon, “Neural network ensembles,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, No. 10, pp. 993-1001, 1990. [cited by applicant]
R.E. Schapire, “The strength of weak learnability,” Machine Learning, vol. 5, No. 2, pp. 197-227, Jun. 1990. [cited by applicant]
L. Breiman, “Bagging predictors,” Machine Learning, vol. 24, No. 2, pp. 123-140, 1996. [cited by applicant]
R.A. Jacobs, M.I. Jordan, S.J. Nowlan, G.E. Hinton, “Adaptive mixtures of local experts,” Neural Computation, vol. 3, No. 1, pp. 79-87, 1991. [cited by applicant]
M.J. Jordan, R.A. Jacobs, “Hierarchical mixtures of experts and the EMalgorithm,” Neural Computation, vol. 6, No. 2, pp. 181-214, 1994. [cited by applicant]
D.H. Wolpert, “Stacked generalization,” Neural Networks, vol. 5, No. 2, pp. 241-259, 1992. [cited by applicant]
J.A. Benediktsson, P.H. Swain, “Consensus theoretic classification methods,” IEEE Transactions on Systems, Man and Cybernetics, vol. 22, No. 4, pp. 688-704, 1992. [cited by applicant]
L. Xu, A. Krzyzak, C.Y. Suen, “Methods of combining multiple classifiers and their applications to handwriting recognition,” IEEE Transactions on Systems, Man and Cybernetics, vol. 22, No. 3, pp. 418-435, 1992. [cited by applicant]
T.K. Ho, J.J. Hull, S.N. Srihari, “Decision combination in multiple classifier systems,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, No. 1, pp. 66-75, 1994. [cited by applicant]
G. Rogova, “Combining the results of several neural network classifiers,” Neural Networks, vol. 7, No. 5, pp. 777-781, 1994. [cited by applicant]
L. Lam, C.Y. Suen, “Optimal combinations of pattern classifiers,” Pattern Recognition Letters, vol. 16, No. 9, pp. 945-954, 1995. [cited by applicant]
K. Woods, W.P.J. Kegelmeyer, K. Bowyer, “Combination of multiple classifiers using local accuracy estimates,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, No. 4, pp. 405-410, 1997. [cited by applicant]
I. Bloch, “Information combination operators for data fusion: A comparative review with classification,” IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans, vol. 26, No. 1, pp. 52-67, 1996. [cited by applicant]
S.B. Cho, J.H. Kim, “Combining multiple neural networks by fuzzy integral for robust classification,” IEEE Transactions on Systems, Man and Cybernetics, vol. 25, No. 2, pp. 380-384, 1995. [cited by applicant]
L.I. Kuncheva, J.C. Bezdek, R.P.W. Duin, “Decision templates for multiple classifier fusion: an experimental comparison,” Pattern Recognition, vol. 34, No. 2, pp. 299-314, 2001. [cited by applicant]
H. Drucker, et al. “Boosting and other ensemble methods,” Neural Computation, vol. 6, No. 6, pp. 1289-1301, 1994. [cited by applicant]
L. I. Kuncheva, “Classifier ensembles for changing environments,” 5th International Workshop on Multiple Classifier Systems in Lecture Notes in Computer Science, eds. F. Roli, J. Kittler, and T. Windeatt, vol. 3077, pp.… [cited by applicant]
R. Avnimelech, N. Intrator, “Boosted mixture of experts: an ensemble learning scheme,” Neural Computation, vol. 11, pp. 483-497, 1999. [cited by applicant]
A.P. Dempster, N.M. Laird, D.B. Rubin, “Maximum likelihood from incomplete data via the EM algorithm,” Journal of the Royal Statistical Society, series B, vol. 39, No. 1, pp. 1-38, 1977. [cited by applicant]
Y. Shim, A. Philippides, K. Staras, P. Husbands, “Unsupervised learning in an ensemble of spiking neural networks mediated by ITDP,” PLOS Computational Biology, vol. 12, pp. 1-41, 2016. [cited by applicant]
B. Nessler, M. Pfeiffer, L. Buesing, W. Maass, “Bayesian computation emerges in generic cortical microcircuits through spike-timing-dependent plasticity,” PLOS Computational Biology, vol. 9, No. 4, pp. 1-30, 2013. [cited by applicant]
E. Chicca, S. Fusi, “Stochastic synaptic plasticity in deterministic a VLSI networks of spiking neurons,” Proceedings of the World Congress on Neuroinformatics, pp. 1-11, 2013. [cited by applicant]
C. Zhang, G. Wang, J. Zhao, P. Gao, J. Lin, H. Yang, “Patient-specific ECG classification based on recurrent neural networks and clustering technique”, IEEE Int. Cont. Biomed. Eng., pp. 63-67, 2017. [cited by applicant]
C. Ribrault, K. Sekimoto, A. Triller, “From the stochasticity of molecular processes to the variability of synaptic transmission,” Nature Rev. Neurosc., vol. 12, pp. 375-387, 2011. [cited by applicant]
E.S. Kuebler, et al., “Stimulus discrimination in networks of spiking neurons,” IEEE Int. Joint Cont. Neur. Netw., pp. 1-8, 2013. [cited by applicant]
M. Kawaguchi, H. Mino, D.M. Durand, “Stochastic resonance can enhance information transmission in neural networks,” IEEE Trans. Neur. Netw., vol. 58, No. 7, pp. 1950-1958, 2011. [cited by applicant]
H. Chen, et al., “Noise-enhanced information systems,” Proc. IEEE, vol. 102, No. 10, pp. 1607-1621, 2014. [cited by applicant]
A.K. Alijani, M.J. Richardson, “Rate response of neurons subject to fast or frozen noise: from stochastic and homogeneous to deterministic and heterogeneous populations,” Physical Review E, vol. 84, No. 1, pp. 1-9, 2011. [cited by applicant]
L. Hertag, D. Durstewitz, N. Brunel, “Analytical approximations of the firing rate of an adaptive exponential integrate-fire neuron in the presence of synaptic noise,” Frontiers in Computational Neuroscience, vol. 8, pp… [cited by applicant]
R.H. Bartels, G.W. Stewart, “Solution of the Matrix Equation AX+XB=C,” Comm. Assoc. Comp. Mach., vol. 15, pp. 820-826, 1972. [cited by applicant]
L. Arnold, Stochastic Differential Equations: Theory and Application, New York: Wiley, 1974. [cited by applicant]
A. Zjajo, et al., “Stochastic analysis of deep-submicrometer CMOS process for reliable circuits designs,” IEEE Transactions on Circuits and Systems-/, vol. 58, No. 1, pp. 164-175, 2011. [cited by applicant]
Y. Hong, J. Wang, D. Cheng, “Adaptive finite-time control of nonlinear systems with parametric uncertainty,” IEEE Transactions on Automatic Control, vol. 51, No. 5, pp. 858-862, 2006. [cited by applicant]
J. Lu, D. Ho, Z. Wang, “Pinning stabilization of linearly coupled stochastic neural networks via minimum number of controllers,” IEEE Transactions on Neural Networks, vol. 20, No. 10, pp. 1617-1629, 2009. [cited by applicant]
J. Cortes, “Finite-time convergent gradient flows with applications to network consensus,” Automatica, vol. 42, No. 11, pp. 1993-2000, 2006. [cited by applicant]
E. Benetos et al., “Automatic Music Transcription: Challenges and future directions,” Journal of Intelligent Information Systems, vol. 41, No. 3, pp. 407-434, Dec. 2013. [cited by applicant]
M.A. Bahari, “Automatic Speaker Characterization—Automatic Identification of Gender, Age, Language and Accent from Speech Signals (PhD Dissertation),” KU Leuven—Faculty of Engineering Science, Heverlee, 2013. [cited by applicant]
E.J. Luz et al., “ECG-based heartbeat classification for arrhythmia detection: A survey,” Computer Methods and Programs in Biomedicine, vol. 127, pp. 144-164, 2016. [cited by applicant]
S. Alavi et al., “Quaternion-Based Gesture Recognition Using Wireless Wearable Motion Capture Sensors,” Sensors, vol. 16, No. 5, 2016. [cited by applicant]
A.Y. Benbasat, J.A. Paradiso, “An Inertial Measurement Framework for Gesture Recognition and Applications,” in Revised Papers from the International Gesture Workshop on Gesture and Sign Languages in Human-Computer Inter… [cited by applicant]
S. Jiang et al., “Development of a real-time hand gesture recognition wristband based on sEMG and IMU sensing,” in International Conference on Robotics and Biomimetics (ROBIO),, 2016. [cited by applicant]
J. Zhu et al., “Automatic Recognition of Radar Signal Based on Time-Frequency Image Shape Character,” Defense Science Journal, vol. 63, No. 3, pp. 308-314, May 2013. [cited by applicant]
W. Maass, “Networks of spiking neurons: The third generation of neural network models,,” Neural Networks, vol. 10, No. 9, pp. 1659-1671, 1997. [cited by applicant]
K.S. Burbank, “Mirrored STDP Implements Autoencoder Learning in a Network of Spiking Neurons,” PLOS Computational Biology, vol. 11, No. 12, pp. 1-24, 2015. [cited by applicant]
Y. Bengio et al., “Greedy Layer-wise Training of Deep Networks,” in Proceedings of the 19th International Conference on Neural Information Processing Systems, 2006. [cited by applicant]
P. Vincent et al., “Extracting and Composing Robust Features with Denoising Autoencoders,” in Proceedings of the 25th International Conference on Machine Learning, 2008. [cited by applicant]
O.E. David, I. Greental, “Genetic Algorithms for Evolving Deep Neural Networks,” in Proceedings of the Companion Publication of the 2014 Annual Conference on Genetic and Evolutionary Computation, 2014. [cited by applicant]
O. Booij, H.T. Nguyen, “A gradient descent rule for spiking neurons emitting multiple spikes,” Information Processing Letters, vol. 95, No. 6, pp. 552-558, 2005. [cited by applicant]
J.H. Lee, T. Delbruck, M. Pfeiffer, “Training Deep Spiking Neural Networks Using Backpropagation,” Frontiers in Neuroscience, vol. 10, p. 508, 2016. [cited by applicant]
Y. Chen, “Mechanisms of Winner-Take-All and Group Selection in Neuronal Spiking Networks,” Frontiers in computational neuroscience, vol. 11, No. 20, 2017. [cited by applicant]
M. Oster, S.C. Liu, “A winner-take-all spiking network with spiking inputs,” in Proceedings of the 2004 11th IEEE International Conference on Electronics, Circuits and Systems, 2004. [cited by applicant]
M. Oster, R. Douglas, S.C. Liu, “Computation with Spikes in a Winner-take-all Network,” Neural Computing, vol. 21, No. 9, pp. 2437-2465, 2009. [cited by applicant]
E. Satuvuori, T. Kreuz, “Which spike train distance is most suitable for distinguishing rate and temporal coding?”, Journal of Neuroscience Methods, vol. 299, pp. 22-33, 2018. [cited by applicant]
J.H. Lee, et al. “Training Deep Spiking Neural Networks Using Backpropagation”, Frontiers in neuroscience, vol. 10, No. 508. Nov. 2016. [cited by applicant]
D.E. Feldman, “The spike-timing dependence of plasticity.” Neuron, vol. 75 No. 4 2012. [cited by applicant]
M. Kawaguchi et al, Analog Neural Circuit with Switched Capacitor and Design of Deep Learning Model, 2015 3rd International Conference on Applied Computing and Information Technology/2nd International Conference on Comp… [cited by applicant]
Shrestha Amar et al: “Stable spike-timing dependent plasticity rule for multilayer unsupervised and supervised learning”,2017 International Joint Conference on Neural Networks (IJCNN), IEEE, May 14, 2017 (May 14, 2017),… [cited by applicant]
Zjajo Amir et al: “Uncertainty in Noise-Driven Steady-State Neuromorphic Network for ECG Data Classification”, 2018 IEEE 31st International Symposium on Computerbased Medical Systems (CBMS), IEEE, Jun. 18, 2018 (Jun. 18… [cited by applicant]
Guillaume Bellec et al: “Deep Rewiring: Training very sparse deep networks”, arxiv.org, Cornell University Library, 201 Olin Library Cornell University Ithaca, NY 14853, Nov. 14, 2017 (Nov. 14, 2017), XP081319720, Aug. … [cited by applicant]
Bernhard Nessler et al: “Bayesian computation emerges in generic cortical microcircuits through spike-timing-dependent plasticity”, PLoS Computational Biology, vol. 9, No. 4, Apr. 25, 2013 (Apr. 25, 2013), p. e1003037, … [cited by applicant]
Michael Pfeiffer et al.: “Deep Learning With Spiking Neurons: Opportunities and Challenges”, Frontiers in Neuroscience, vol. 12, Oct. 25, 2018, XP055570520, CH, ISSN: 1662-4548, DOI: 10.3389/fnins.2018.00774. [cited by applicant]