A Radial Basis Function Spike Model for Indirect Learning via Integrate-and-Fire Sampling and Reconstruction Techniques

Abstract

This paper presents a deterministic and adaptive spike model derived from radial basis functions and a leaky integrate-and-fire sampler developed for training spiking neural networks without direct weight manipulation. Several algorithms have been proposed for training spiking neural networks through biologically-plausible learning mechanisms, such as spike-timing-dependent synaptic plasticity and Hebbian plasticity. These algorithms typically rely on the ability to update the synaptic strengths, or weights, directly, through a weight update rule in which the weight increment can be decided and implemented based on the training equations. However, in several potential applications of adaptive spiking neural networks, including neuroprosthetic devices and CMOS/memristor nanoscale neuromorphic chips, the weights cannot be manipulated directly and, instead, tend to change over time by virtue of the pre- and postsynaptic neural activity. This paper presents an indirect learning method that induces changes in the synaptic weights by modulating spike-timing-dependent plasticity by means of controlled input spike trains. In place of the weights, the algorithm manipulates the input spike trains used to stimulate the input neurons by determining a sequence of spike timings that minimize a desired objective function and, indirectly, induce the desired synaptic plasticity in the network.

Supervised Learning in SNN via Reward-Modulated Spike-Timing-Dependent Plasticity for a Target Reaching Vehicle

“…This was then used to train a simulated flying insect robot to follow a flight trajectory in Clawson et al (2016). Similar ideas were presented by Zhang et al (2012, 2013), Hu et al (2014), and Mazumder et al (2016) who trained a simple, virtual insect in a target reaching and obstacle avoidance task. However, this method is not suited for training an SNN on multi-dimensional inputs since the reward is dependent on the sign of the difference between the desired and actual SNN output.…”

A Survey of Robotics Control Based on Learning-Inspired Spiking Neural Networks

“…By minimizing the error between control output and optimal control law offline, it was able to learn adaptive control of an aircraft. Similar ideas were presented by Zhang et al ( 2012 ), Zhang et al ( 2013 ), Hu et al ( 2014 ), and Mazumder et al ( 2016 ) who trained a simple, virtual insect in a target reaching and obstacle avoidance task.…”

WebVRGIS based traffic analysis and visualization system

“…[29] [30][31] [32][33], enhanced vision feedback technologies[34] [35][36] [37][38], network technologies[39] [40][41] [42], bigdata[43] [44] [45][46] and some optimization approaches[47] [48][49] [50][51] …”