Indirect and Direct Training of Spiking Neural Networks for End-to-End Control of a Lane-Keeping Vehicle

03/10/2020
by   Zhenshan Bing, et al.
9

Building spiking neural networks (SNNs) based on biological synaptic plasticities holds a promising potential for accomplishing fast and energy-efficient computing, which is beneficial to mobile robotic applications. However, the implementations of SNNs in robotic fields are limited due to the lack of practical training methods. In this paper, we therefore introduce both indirect and direct end-to-end training methods of SNNs for a lane-keeping vehicle. First, we adopt a policy learned using the blackDeep Q-Learning (DQN) algorithm and then subsequently transfer it to an SNN using supervised learning. Second, we adopt the reward-modulated spike-timing-dependent plasticity (R-STDP) for training SNNs directly, since it combines the advantages of both reinforcement learning and the well-known spike-timing-dependent plasticity (STDP). We examine the proposed approaches in three scenarios in which a robot is controlled to keep within lane markings by using an event-based neuromorphic vision sensor. We further demonstrate the advantages of the R-STDP approach in terms of the lateral localization accuracy and training time steps by comparing them with other three algorithms presented in this paper.

READ FULL TEXT

page 3

page 10

page 19

page 25

page 26

page 28

page 30

research
03/26/2020

Spike-Timing-Dependent Back Propagation in Deep Spiking Neural Networks

The success of Deep Neural Networks (DNNs) can be attributed to its deep...
research
06/04/2020

Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks

For the gradient computation across the time domain in Spiking Neural Ne...
research
05/31/2021

Characterization of Generalizability of Spike Timing Dependent Plasticity trained Spiking Neural Networks

A Spiking Neural Network (SNN) is trained with Spike Timing Dependent Pl...
research
08/31/2016

Training Deep Spiking Neural Networks using Backpropagation

Deep spiking neural networks (SNNs) hold great potential for improving t...
research
10/02/2019

An Introduction to Probabilistic Spiking Neural Networks

Spiking neural networks (SNNs) are distributed trainable systems whose c...
research
04/22/2016

evt_MNIST: A spike based version of traditional MNIST

Benchmarks and datasets have important role in evaluation of machine lea...
research
09/25/2012

Towards a learning-theoretic analysis of spike-timing dependent plasticity

This paper suggests a learning-theoretic perspective on how synaptic pla...

Please sign up or login with your details

Forgot password? Click here to reset