Training deep spiking neural networks using backpropagation
Deep spiking neural networks (SNNs) hold the potential for improving the latency and
energy efficiency of deep neural networks through data-driven event-based computation …
energy efficiency of deep neural networks through data-driven event-based computation …
A configurable simulation environment for the efficient simulation of large-scale spiking neural networks on graphics processors
Neural network simulators that take into account the spiking behavior of neurons are useful
for studying brain mechanisms and for various neural engineering applications. Spiking …
for studying brain mechanisms and for various neural engineering applications. Spiking …
Round-trip engineering apparatus and methods for neural networks
B Szatmary, EM Izhikevich, C Petre… - US Patent …, 2015 - Google Patents
Apparatus and methods for high-level neuromorphic network description (HLND) framework
that may be configured to enable users to define neuromorphic network architectures using …
that may be configured to enable users to define neuromorphic network architectures using …
Artificial to spiking neural networks conversion for scientific machine learning
We introduce a method to convert Physics-Informed Neural Networks (PINNs), commonly
used in scientific machine learning, to Spiking Neural Networks (SNNs), which are expected …
used in scientific machine learning, to Spiking Neural Networks (SNNs), which are expected …
High level neuromorphic network description apparatus and methods
B Szatmary, EM Izhikevich, C Petre… - US Patent …, 2019 - Google Patents
Primary Examiner—Eric Nilsson (74) Attorney, Agent, or Firm—Seyfarth Shaw LLP (57)
ABSTRACT Apparatus and methods for high-level neuromorphic net work description …
ABSTRACT Apparatus and methods for high-level neuromorphic net work description …
Elementary network description for neuromorphic systems with plurality of doublets wherein doublet events rules are executed in parallel
EM Izhikevich, B Szatmary, C Petre… - US Patent …, 2015 - Google Patents
A simple format is disclosed and referred to as Elementary Network Description (END). The
format can fully describe a large-scale neuronal model and embodiments of software or …
format can fully describe a large-scale neuronal model and embodiments of software or …
Efficient simulation of large-scale spiking neural networks using CUDA graphics processors
Neural network simulators that take into account the spiking behavior of neurons are useful
for studying brain mechanisms and for engineering applications. Spiking neural network …
for studying brain mechanisms and for engineering applications. Spiking neural network …
Adaptive learning rate of SpikeProp based on weight convergence analysis
SB Shrestha, Q Song - Neural Networks, 2015 - Elsevier
Abstract A Spiking Neural Network (SNN) training using SpikeProp and its variants is usually
affected by sudden rise in learning cost called surges. These surges cause diversion in the …
affected by sudden rise in learning cost called surges. These surges cause diversion in the …
GPU-based simulation of spiking neural networks with real-time performance & high accuracy
A novel GPU-based simulation of spiking neural networks is implemented as a hybrid
system using Parker-Sochacki numerical integration method with adaptive order. Full single …
system using Parker-Sochacki numerical integration method with adaptive order. Full single …
A 3232 Pixel Convolution Processor Chip for Address Event Vision Sensors With 155 ns Event Latency and 20 Meps Throughput
This paper describes a convolution chip for event-driven vision sensing and processing
systems. As opposed to conventional frame-constraint vision systems, in event-driven vision …
systems. As opposed to conventional frame-constraint vision systems, in event-driven vision …