A low cost neuromorphic learning engine based on a high performance supervised SNN learning algorithm

Abstract

Spiking neural networks (SNNs) are more energy- and resource-efficient than artificial neural networks (ANNs). However, supervised SNN learning is a challenging task due to non-differentiability of spikes and computation of complex terms. Moreover, the design of SNN learning engines is not an easy task due to limited hardware resources and tight energy constraints. In this article, a novel hardware-efficient SNN back-propagation scheme that offers fast convergence is proposed. The learning scheme does not require any complex operation such as error normalization and weight-threshold balancing, and can achieve an accuracy of around 97.5% on MNIST dataset using only 158,800 synapses. The multiplier-less inference engine trained using the proposed hard sigmoid SNN training (HaSiST) scheme can operate at a frequency of 135 MHz and consumes only 1.03 slice registers per synapse, 2.8 slice look-up tables, and can infer about 0.03$$\times {\varvec{10}}^{\varvec{9}}$$ × 10 9 features in a second, equivalent to 9.44 giga synaptic operations per second (GSOPS). The article also presents a high-speed, cost-efficient SNN training engine that consumes only 2.63 slice registers per synapse, 37.84 slice look-up tables per synapse, and can operate at a maximum computational frequency of around 50 MHz on a Virtex 6 FPGA.

PRC-Light YOLO: An Efficient Lightweight Model for Fabric Defect Detection

“…The computation process of the Sigmoid function involves exponentiation, which undoubtedly increases the computational complexity of the SiLU activation function. However, the Sigmoid activation function can be approximated using a piecewise linear function called HardSigmoid [36], which significantly reduces the computational cost. The HardSigmoid activation function and HardSwish activation function expressions are as follows:…”

Maximum Lyapunov exponent-based multiple chaotic slime mold algorithm for real-world optimization

“…Based on the kinematic properties of chaotic behavior, a plausible screening mechanism is established to guide the search pattern of the local operator. In addition, considering the search behaviors and trajectories of slime mold individuals in MCSMA, we expect to explore a general way to refine the underlying search logic of the algorithm and guide the algorithm to improve its reliability throughout the search process 44 , 45 .…”

SpikoPoniC: A Low-Cost Spiking Neuromorphic Computer for Smart Aquaponics

“…Furthermore, we focus not only on the algorithm but also on the hardware design. This approach has been proven to be extremely effective at developing high-performance systems [9,22] since hardware efficiency is directly related to algorithmic efficiency.…”

“…Therefore, SNNs are more bioplausible than ANNs [12,13]. In fact, since SNNs use simple spikes, they might have a very small hardware footprint, as in [9,14]. Moreover, SNNs can achieve almost the same level of accuracy as ANNs, as can be seen in [14][15][16].…”

“…NMAs are accelerators that use dedicated hardware devices (FPGAs/ASICs) to implement neural networks. By doing so, a lot of improvement in system speed, energy consumption, and area can be obtained [8,9]. Section 1.2 discusses various modern neuromorphic accelerators.…”