Improved integrate-and-fire neuron models for inference acceleration of spiking neural networks

We study the effects of different bio-synaptic membrane potential mechanisms on the inference speed of both spiking feed-forward neural networks and spiking convolutional neural networks. These mechanisms are inspired by biological neuron phenomena include electronic conduction in neurons and chemical neurotransmitter attenuation between presynaptic and postsynaptic neurons. In the area of spiking neural networks, we model some biological neural membrane potential updating strategies based on integrate-and-fire (I&F) spiking neurons. These include the spiking neuron model with membrane potential decay (MemDec), the spiking neuron model with synaptic input current superposition at spiking time (SynSup), and the spiking neuron model with synaptic input current accumulation (SynAcc). Experiment results show that compared with the general I&F model (one of the most commonly used spiking neuron models), SynSup and SynAcc can effectively improve the spiking inference speed of spiking feed-forward neural networks and spiking convolutional neural networks.

• Publication year

  2019

• Venue

  Applied intelligence (Boston)

• Publication date

  2019-12-19

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1007/s10489-020-02017-3
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Intrinsic Plasticity Based Inference Acceleration for Spiking Multi-Layer Perceptron

  2019cited by this paper
• Fast and robust learning in Spiking Feed-forward Neural Networks based on Intrinsic Plasticity mechanism

  2019cited by this paper
• Homeostatic Fault Tolerance in Spiking Neural Networks: A Dynamic Hardware Perspective

  2018cited by this paper
• Quantisation and pooling method for low-inference-latency spiking neural networks

  2017cited by this paper
• A fast learning algorithm of self-learning spiking neural network

  2016cited by this paper
• Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks

  2016cited by this paper
• Spiking Deep Convolutional Neural Networks for Energy-Efficient Object Recognition

  2015cited by this paper
• Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing

  2015influential reference
• A Computationally Efficient Method for Incorporating Spike Waveform Information into Decoding Algorithms

  2015cited by this paper
• On the Capabilities and Computational Costs of Neuron Models

  2014cited by this paper
• An efficient automated parameter tuning framework for spiking neural networks

  2014cited by this paper
• Associative Hebbian Synaptic Plasticity in Primate Visual Cortex

  2014cited by this paper
• Real-time classification and sensor fusion with a spiking deep belief network

  2013cited by this paper
• An Event-Driven Multi-Kernel Convolution Processor Module for Event-Driven Vision Sensors

  2012cited by this paper
• Stimulus timing-dependent plasticity in high-level vision.

  2012cited by this paper
• A digital neurosynaptic core using embedded crossbar memory with 45pJ per spike in 45nm

  2011cited by this paper
• Decoding Poisson Spike Trains by Gaussian Filtering

  2010cited by this paper
• Spiking Neural Networks for Cortical Neuronal Spike Train Decoding

  2010cited by this paper
• Et al

  2008cited by this paper
• Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity

  2007cited by this paper
• Solution Methods for a New Class of Simple Model Neurons

  2007cited by this paper
• The tempotron: a neuron that learns spike timing–based decisions

  2006cited by this paper
• Receptive-field modification in rat visual cortex induced by paired visual stimulation and single-cell spiking.

  2006cited by this paper
• Learning Beyond Finite Memory in Recurrent Networks of Spiking Neurons

  2005cited by this paper
• Improving SpikeProp: Enhancements to An Error-Backpropagation Rule for Spiking Neural Networks

  2004cited by this paper
• Fast Propagation of Firing Rates through Layered Networks of Noisy Neurons

  2002cited by this paper
• Error-backpropagation in temporally encoded networks of spiking neurons

  2000cited by this paper
• Networks of spiking neurons: the third generation of neural network models

  1997cited by this paper
• Networks of Spiking Neurons: The Third Generation of Neural Network Models

  1996cited by this paper
• Particle swarm optimization

  1995cited by this paper

• Design of energy-efficient LIF neuron using CMOS compatible gate-all-around floating nanosheet FET for bio-inspired spiking neural networks

  2026cites this paper
• Dynamic spatio-temporal pruning for efficient spiking neural networks

  2025cites this paper
• Learning improvement of spiking neural networks with dynamic adaptive hyperparameter neurons

  2024cites this paper
• Two-Terminal Neuromorphic Devices for Spiking Neural Networks: Neurons, Synapses, and Array Integration.

  2024cites this paper
• HNSG – A SNN Training Method Ultilizing Hidden Network

  2023cites this paper
• Highway Connection for Low-Latency and High-Accuracy Spiking Neural Networks

  2023cites this paper
• Review of Closed-Loop Brain–Machine Interface Systems From a Control Perspective

  2022cites this paper
• Small-world spiking neural network with anti-interference ability based on speech recognition under interference

  2022cites this paper
• Visible-light stimulated synaptic plasticity in amorphous indium-gallium-zinc oxide enabled by monocrystalline double perovskite for high-performance neuromorphic applications

  2022cites this paper
• Visible Light-Driven Indium-Gallium-Zinc-Oxide Optoelectronic Synaptic Transistor with Defect Engineering for Neuromorphic Computing System and Artificial Intelligence

  2022cites this paper
• Bifurcation Analysis of a Two-Dimensional Neuron Model under Electrical Stimulation

  2021cites this paper