US 12,380,320 B2
Resilient neural network
Amir Zjajo, The Hague (NL); and Sumeet Susheel Kumar, The Hague (NL)
Assigned to INNATERA NANOSYSTEMS B.V., Rijswijk (NL)
Appl. No. 17/294,697
Filed by Innatera Nanosystems B.V., Rijswijk (NL)
PCT Filed Nov. 18, 2019, PCT No. PCT/EP2019/081662
§ 371(c)(1), (2) Date May 18, 2021,
PCT Pub. No. WO2020/099680, PCT Pub. Date May 22, 2020.
Claims priority of provisional application 62/768,927, filed on Nov. 18, 2018.
Prior Publication US 2022/0012564 A1, Jan. 13, 2022
Int. Cl. G06N 3/049 (2023.01); G06N 3/045 (2023.01); G06N 3/063 (2023.01); G06N 3/08 (2023.01)
CPC G06N 3/049 (2013.01) [G06N 3/045 (2023.01); G06N 3/063 (2013.01); G06N 3/08 (2013.01)] 16 Claims
OG exemplary drawing
 
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 Γi of the spiking neuron i in the spiking neural network, wherein the synaptic drive Γi 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 Γi; lies below a predetermined value such that the synaptic drive Γi, of each of the neuron i in the spiking neural network is bound around an equilibrium point Γi of the synaptic drive Γi, where noise effects are minimal.