Holographic Graph Neuron: a Bio-Inspired Architecture for Pattern Processing

Abstract

This article proposes the use of Vector Symbolic Architectures for implementing Hierarchical Graph Neuron, an architecture for memorizing patterns of generic sensor stimuli. The adoption of a Vector Symbolic representation ensures a one-layered design for the approach, while maintaining the previously reported properties and performance characteristics of Hierarchical Graph Neuron, and also improving the noise resistance of the architecture. The proposed architecture enables a linear (with respect to the number of stored entries) time search for an arbitrary sub-pattern.

9 pages, 13 figures

Cited by in corpus (10)

• Classification using Hyperdimensional Computing: A Review
• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations
• Integer Echo State Networks: Efficient Reservoir Computing for Digital Hardware
• HyperEmbed: Tradeoffs Between Resources and Performance in NLP Tasks with Hyperdimensional Computing enabled Embedding of n-gram Statistics
• Neural Distributed Autoassociative Memories: A Survey
• Perceptron Theory Can Predict the Accuracy of Neural Networks
• An Encoding Framework for Binarized Images using HyperDimensional Computing
• Efficient Decoding of Compositional Structure in Holistic Representations
• Robust Clustering using Hyperdimensional Computing
• Cellular Automata Can Reduce Memory Requirements of Collective-State Computing