Integer Echo State Networks: Efficient Reservoir Computing for Digital Hardware

Abstract

We propose an approximation of Echo State Networks (ESN) that can be efficiently implemented on digital hardware based on the mathematics of hyperdimensional computing. The reservoir of the proposed integer Echo State Network (intESN) is a vector containing only n-bits integers (where n<8 is normally sufficient for a satisfactory performance). The recurrent matrix multiplication is replaced with an efficient cyclic shift operation. The proposed intESN approach is verified with typical tasks in reservoir computing: memorizing of a sequence of inputs; classifying time-series; learning dynamic processes. Such architecture results in dramatic improvements in memory footprint and computational efficiency, with minimal performance loss. The experiments on a field-programmable gate array confirm that the proposed intESN approach is much more energy efficient than the conventional ESN.

13 pages, 11 figures, 5 tables

References in corpus (2)

• Brain-inspired photonic signal processor for periodic pattern generation and chaotic system emulation
• Density Encoding Enables Resource-Efficient Randomly Connected Neural Networks

Cited by in corpus (7)

• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges
• Vector Symbolic Architectures as a Computing Framework for Emerging Hardware
• Underwater Acoustic Communication Channel Modeling using Reservoir Computing
• Perceptron Theory Can Predict the Accuracy of Neural Networks
• Reservoir Network with Structural Plasticity for Human Activity Recognition
• A novel Reservoir Architecture for Periodic Time Series Prediction
• Cellular Automata Can Reduce Memory Requirements of Collective-State Computing