Entropic Associative Memory for Manuscript Symbols

TL;DR

This paper introduces an entropic associative memory system for manuscript symbols that allows recognition and retrieval based on entropy-controlled trade-offs, enabling efficient handling of incomplete data and contrasting with neural network models.

Contribution

The paper presents a novel entropic associative memory framework that is distributed, declarative, and capable of constructive retrieval without search, differing from neural network approaches.

Findings

Memory retrieval quality depends on entropy levels.

The system effectively recognizes incomplete and occluded symbols.

Experimental results support potential practical applications.

Abstract

Manuscript symbols can be stored, recognized and retrieved from an entropic digital memory that is associative and distributed but yet declarative; memory retrieval is a constructive operation, memory cues to objects not contained in the memory are rejected directly without search, and memory operations can be performed through parallel computations. Manuscript symbols, both letters and numerals, are represented in Associative Memory Registers that have an associated entropy. The memory recognition operation obeys an entropy trade-off between precision and recall, and the entropy level impacts on the quality of the objects recovered through the memory retrieval operation. The present proposal is contrasted in several dimensions with neural networks models of associative memory. We discuss the operational characteristics of the entropic associative memory for retrieving objects with both complete and incomplete information, such as severe occlusions. The experiments reported in this paper add evidence on the potential of this framework for developing practical applications and computational models of natural memory.