Density Encoding Enables Resource-Efficient Randomly Connected Neural Networks

TL;DR

This paper introduces a density encoding method for resource-efficient randomly connected neural networks, improving accuracy and reducing energy consumption on edge devices through hyperdimensional computing techniques and FPGA implementation.

Contribution

It proposes a novel density-based encoding for RVFL networks, enhancing accuracy and enabling integer-only representations for efficient hardware deployment.

Findings

Higher average accuracy than conventional RVFL

Integer-based readout matrix with minimal accuracy loss

Approximately eleven times less energy consumption on FPGA

Abstract

The deployment of machine learning algorithms on resource-constrained edge devices is an important challenge from both theoretical and applied points of view. In this article, we focus on resource-efficient randomly connected neural networks known as Random Vector Functional Link (RVFL) networks since their simple design and extremely fast training time make them very attractive for solving many applied classification tasks. We propose to represent input features via the density-based encoding known in the area of stochastic computing and use the operations of binding and bundling from the area of hyperdimensional computing for obtaining the activations of the hidden neurons. Using a collection of 121 real-world datasets from the UCI Machine Learning Repository, we empirically show that the proposed approach demonstrates higher average accuracy than the conventional RVFL. We also demonstrate that it is possible to represent the readout matrix using only integers in a limited range with minimal loss in the accuracy. In this case, the proposed approach operates only on small n-bits integers, which results in a computationally efficient architecture. Finally, through hardware Field-Programmable Gate Array (FPGA) implementations, we show that such an approach consumes approximately eleven times less energy than that of the conventional RVFL.