Skip to main content
Ctrl+K
3.1.3 - Home
  • GETTING STARTED
    • Installation
    • Fundamentals of Sinabs
    • A quick (and over-simplified) introduction to spiking neurons
    • Quickstart Sinabs
    • Python versions, pyenv and pipenv
  • Speck
    • Overview
    • The Basics
    • Advanced
    • Dangers
    • Dynapcnn Visualizer
    • Specksim
    • FAQs
      • Troubleshooting and Tips
      • Chip Errata(Hardware Bugs)
      • Available Network Architecture
      • Available Operations
      • Device Management
      • Output Monitoring
      • Save Samna Config As Binary
      • How to add support for a new chip
      • How To Leak The Neurons On The Devkit
  • SINABS GALLERY
    • Neuron models
      • Exponential Leaky Layer (ExpLeak)
      • Adaptive Leaky Integrate and Fire (ALIF)
      • Integrate and Fire (IAF)
      • Leaky Integrate and Fire (LIF)
      • Utility Function
    • Spike functions
      • MultiSpike
      • SingleSpike
      • MaxSpike
    • Surrogate gradient functions
      • Gaussian
      • Heaviside
      • MultiGaussian
      • SingleExponential
      • PeriodicExponential
  • TUTORIALS
    • Training by backpropagation through time (BPTT)
    • Converting an ANN to an SNN
    • Training NMNIST for deployment on Speck using EXODUS
    • Scaling parameters for rate-coded conversion to SNNs
    • Import a model from NIR and deploy it to SPECK
    • sinabs Tutorial 使用入门
    • Hardware Tutorials
      • Quick Start With N-MNIST
      • Visualize DVS Input
      • Play With Speck’s DVS
      • How To Leak The Neurons On The Devkit
      • Power Monitoring
      • Spike Count Visualization
      • Using Readout Layer
  • HOW TOS
    • Training an ANN with fewer SynOps
    • Training an SNN with fewer SynOps and monitoring the firing rate
    • Add custom hooks to monitor network properties
    • Change activations in spiking layers
  • PLUGINS
  • API REFERENCE
    • network
    • layers
      • StatefulLayer
      • SqueezeMixin
      • IAF
      • IAFSqueeze
      • IAFRecurrent
      • LIF
      • LIFSqueeze
      • LIFRecurrent
      • ALIF
      • ALIFRecurrent
      • ExpLeak
      • ExpLeakSqueeze
      • SpikingMaxPooling2dLayer
      • SumPool2d
      • Img2SpikeLayer
      • Sig2SpikeLayer
      • Cropping2dLayer
      • Repeat
      • FlattenTime
      • UnflattenTime
      • NeuromorphicReLU
      • QuantizeLayer
    • activation
      • SingleSpike
      • MultiSpike
      • MaxSpike
      • MembraneReset
      • MembraneSubtract
      • SingleExponential
      • PeriodicExponential
      • Heaviside
      • Gaussian
      • MultiGaussian
    • from_torch
    • hooks
    • SynOpCounter
    • utils
    • nir
    • sinabs.backend.dynapcnn
      • chip_factory
      • config_builder
      • crop2d
      • discretize
      • dvs_layer
      • dynapcnn_network
      • dynapcnn_layer
      • exceptions
      • flipdims
      • io
      • mapping
      • utils
      • dynapcnn_visualizer
      • specksim
  • ABOUT
    • About this project
    • How is Sinabs different?
    • Contributing to sinabs
    • Release notes
  • CONTACT US
  • Repository
  • Suggest edit
  • Open issue
  • .rst

SINABS GALLERY

Contents

  • Neuron models
  • Spike functions
  • Surrogate gradient functions

SINABS GALLERY#

Neuron models#

Exponential Leaky Layer (ExpLeak)

Exponential Leaky Layer (ExpLeak)

Adaptive Leaky Integrate and Fire (ALIF)

Adaptive Leaky Integrate and Fire (ALIF)

Integrate and Fire (IAF)

Integrate and Fire (IAF)

Leaky Integrate and Fire (LIF)

Leaky Integrate and Fire (LIF)

Utility Function

Utility Function

Spike functions#

MultiSpike

MultiSpike

SingleSpike

SingleSpike

MaxSpike

MaxSpike

Surrogate gradient functions#

Gaussian

Gaussian

Heaviside

Heaviside

MultiGaussian

MultiGaussian

SingleExponential

SingleExponential

PeriodicExponential

PeriodicExponential

Gallery generated by Sphinx-Gallery

previous

How To Leak The Neurons On The Devkit

next

Neuron models

Contents
  • Neuron models
  • Spike functions
  • Surrogate gradient functions

By employees of SynSense

© Copyright 2019-present, SynSense.