# Content-Addressable Memory with a Content-Free Energy Function

Source: [Content-Addressable Memory with a Content-Free Energy Function](<https://www.sota2.com/research/paper/68fa49c41e209131ce9396be>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-19T05:01:30.460Z

Authors: F\\'elix Benoist, Luca Peliti, Pablo Sartori

Published: 2025-03-24T16:01:09.000Z

## Abstract

Content-addressable memory, i.e. stored information that can be retrieved from content-based cues, is key to computation. Besides natural and artificial neural networks, physical learning systems have recently been shown to have remarkable ability in this domain. While classical neural network models encode memories as energy minima, biochemical systems have been shown to be able to process information based on purely kinetic principles. This opens the question of whether neural networks can also encode information kinetically. Here, we propose a minimal model for content-addressable memory in which the kinetics, and not the energy function, are used to encode patterns. We find that the performance of this kinetic encoding approach is comparable to that of classical energy-based encoding schemes. This highlights the fundamental significance of the kinetic stability of kinetic traps as an alternative to the thermodynamic stability of energy minima, offering new insights into the principles of computation in physical and synthetic systems.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.18822>)

[PDF](<https://arxiv.org/pdf/2503.18822.pdf>)
