Brain-Inspired Spiking Neural Networks

Abstract

Brain is a very efficient computing system. It performs very complex tasks while occupying about 2 liters of volume and consuming very little energy. The computation tasks are performed by special cells in the brain called neurons. They compute using electrical pulses and exchange information between them through chemicals called neurotransmitters. With this as inspiration, there are several compute models which exist today trying to exploit the inherent efficiencies demonstrated by nature. The compute models representing spiking neural networks (SNNs) are biologically plausible, hence are used to study and understand the workings of brain and nervous system. More importantly, they are used to solve a wide variety of problems in the field of artificial intelligence (AI). They are uniquely suited to model temporal and spatio-temporal data paradigms. This chapter explores the fundamental concepts of SNNs, few of the popular neuron models, how the information is represented, learning methodologies, and state of the art platforms for implementing and evaluating SNNs along with a discussion on their applications and broader role in the field of AI and data networks.

Machine learning with a snapshot of data: Spiking neural network ‘predicts’ reinforcement histories of pigeons' choice behavior

“…This was achievable using the Leaky Integrate‐and‐Fire (LIF) model, a mathematical representation of a neuron that was trained to perform the task. The LIF model is commonly used due to its simplicity and computational efficiency while attempting to mimic biology (see, e.g., Ahmed, 2020, for more on neuron models).…”

Spike-based computational models of bio-inspired memories in the hippocampal CA3 region on SpiNNaker

“…In order to implement bio-inspired memory models based on the hippocampus, third-generation of neural networks, i.e., SNNs, were used. This kind of networks consists of interconnected neuron models that are not only inspired by biology, but also attempt to mimic their biological counterparts, in order to incorporate the neurocomputational capabilities found in nature [5].…”

“…This aspect makes SNNs very efficient from a computational point of view. Moreover, SNNs present a distributed learning process thanks to the use of Spike-timing-dependent plasticity (STDP) [25], which obtains the necessary information from the electrical impulses encoded between local neurons to define the weight of the synapses, i.e., to regulate the learning of the network [5].…”

“…These are able to process asynchronous spikes instead of floating point or integer numbers, as traditional artificial neural networks would do. SNNs consists of bioinspired neuron models, which are interconnected by means of synapses, and mimic the way in which the senses and the brain process the information in living organisms [5]. In the last years, SNNs have been used for many different tasks, such as speech recognition [6], [7], image classification [8], [9], sensory fusion [8], [10], motor control [11], [12] and bioinspired locomotion [13]- [15], among many others, proving that they could be useful in a wide variety of fields and allowing more efficient and lower power-consumption devices to perform in the same manner as their traditional counterparts.…”

A Brief Review on Spiking Neural Network - A Biological Inspiration<b> </b>

“…SNN can overcome the drawbacks of heuristic methods on data clustering [12]. SNNs are intriguing a direct result of their capacity to learn in a circulated manner utilizing a strategy called Spike Timing Dependent Plasticity (STDP) learning [11]. SNN structure that can be initially mapped to specific kinds of spikebased neuromorphic equipment with less execution loss [18].…”