'Memory States' from Almost Nothing: Representing and Computing in a Non-associative Algebra

TL;DR

This paper introduces a non-associative algebraic framework for representing and computing memory sequences in high-dimensional space, capturing temporal structure and effects like recency and primacy without auxiliary order markers.

Contribution

It proposes a novel non-associative bundling method that preserves sequence order and temporal information inherently, unlike traditional associative models.

Findings

Replicates the Serial Position Curve observed in cognitive experiments.

Differentiates between recency and primacy effects through distinct memory states.

Supports long sequences with sparse, order-preserving representations.

Abstract

This note presents a non-associative algebraic framework for the representation and computation of information items in high-dimensional space. This framework is consistent with the principles of spatial computing and with the empirical findings in cognitive science about memory. Computations are performed through a process of multiplication-like binding and non-associative interference-like bundling. Models that rely on associative bundling typically lose order information, which necessitates the use of auxiliary order structures, such as position markers, to represent sequential information that is important for cognitive tasks. In contrast, the non-associative bundling proposed allows the construction of sparse representations of arbitrarily long sequences that maintain their temporal structure across arbitrary lengths. In this operation, noise is a constituent element of the representation of order information, rather than a means of obscuring it. The non-associative nature of the proposed framework results in the representation of a single sequence by two distinct states. The L-state, generated through left-associative bundling, continuously updates and emphasises a recency effect, while the R-state, formed through right-associative bundling, encodes finite sequences or chunks, capturing a primacy effect. The construction of these states may be associated with activity in the prefrontal cortex in relation to short-term memory and hippocampal encoding in long-term memory, respectively. The accuracy of retrieval is contingent upon a decision-making process that is based on the mutual information between the memory states and the cue. The model is able to replicate the Serial Position Curve, which reflects the empirical recency and primacy effects observed in cognitive experiments.