Temporal-Rate Encoding to Realize Unary Positional Representation in Spiking Neural Systems

TL;DR

This paper proposes a hybrid unary positional encoding method for spiking neural systems that combines the error tolerance of unary encoding with the compactness of positional representation by using temporal and rate encoding.

Contribution

It introduces a novel unary positional encoding scheme that leverages temporal and rate encoding to improve latency and error tolerance in spiking neural systems.

Findings

Hybrid encoding reduces latency compared to pure unary methods.

The approach maintains high error tolerance similar to unary encoding.

It achieves a more compact representation than traditional unary encoding.

Abstract

Unary representation is straightforward, error tolerant and requires simple logic while its latency is a concern. On the other hand, positional representation (like binary) is compact and requires less space, but it is sensitive to errors. A hybrid representation called unary positional encoding reduces the latency of unary computation and length of the encoded stream, thus achieves the compactness of positional representation while preserving the error tolerance of unary encoding. In this paper, we discuss the prospect of unary positional encoding in spiking neural systems by incorporating temporal and rate encoding.