Improved Cleanup and Decoding of Fractional Power Encodings

TL;DR

This paper introduces an iterative optimization approach combining CLE and MLE to improve decoding and cleanup of continuous-valued FHRR vectors, enhancing robustness against noise in high-dimensional neural representations.

Contribution

It presents a novel iterative optimization method for decoding and cleaning up Fourier Holographic Reduced Representation vectors encoding continuous values, outperforming existing techniques.

Findings

Effective decoding under various noise conditions.

Outperforms existing cleanup methods.

Ensures convergence to the global optimum.

Abstract

High-dimensional vectors have been proposed as a neural method for representing information in the brain using Vector Symbolic Algebras (VSAs). While previous work has explored decoding and cleaning up these vectors under the noise that arises during computation, existing methods are limited. Cleanup methods are essential for robust computation within a VSA. However, cleanup methods for continuous-value encodings are not as effective. In this paper, we present an iterative optimization method to decode and clean up Fourier Holographic Reduced Representation (FHRR) vectors that are encoding continuous values. We combine composite likelihood estimation (CLE) and maximum likelihood estimation (MLE) to ensure convergence to the global optimum. We also demonstrate that this method can effectively decode FHRR vectors under different noise conditions, and show that it outperforms existing methods.