Spiking Neural Networks for Sustainable and High-Performance Computing
Authors:
- 9 July 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1030-1035
Abstract
Neuromorphic computing is defined as a non-von Neumann computation, unlike Von Neuman computation which consists of a separate CPU and memory unit, where data and instructions are stored in a unified memory unit. Neuromorphic computing whose structure is inspired by brains composed of neurons and synapses uses spikes as input, capturing the timing and interval between spikes to encode numerical information. it is ideal for systems that require high parallel operation, neuromorphic systems are highly scalable, and event-driven which allows for efficient computation. These neurological and biological mechanisms are modeled in neuromorphic computing systems through spiking neural networks (SNNs), In SNNs the information is coded with time-dependent spikes, which remarkably reduces the power consumption, our proposed solutions result indicate improved learning capacity and reduced power consumption compared to traditional computing approaches.Keywords
This publication has 17 references indexed in Scilit:
- Advancing Audio Fingerprinting Accuracy with AI and ML: Addressing Background Noise and Distortion Challenges2024
- A spiking neural network model of 3D perception for event-based neuromorphic stereo vision systemsScientific Reports, 2017
- Scaling-up resistive synaptic arrays for neuro-inspired architecture: Challenges and prospect2015
- NVM neuromorphic core with 64k-cell (256-by-256) phase change memory synaptic array with on-chip neuron circuits for continuous in-situ learning2015
- Asynchronous frameless event-based optical flowNeural Networks, 2012
- Analog VLSI Biophysical Neurons and Synapses With Programmable Membrane Channel KineticsIEEE Transactions on Biomedical Circuits and Systems, 2010
- The missing memristor foundNature, 2008
- Neuromimetic ICs with analog cores: an alternative for simulating spiking neural networks2007
- Asymmetric cross-coupled differential pair configuration to realize neuron activation function and its derivativeIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 2005
- Binary Neural Networks – A CMOS Design Approach2005