Attractor Properties of Spatiotemporal Memory in Effective Sequence Processing Task-Reference-Cited by-同舟云学术

Attractor Properties of Spatiotemporal Memory in Effective Sequence Processing Task

Published:2023-11-28 Issue:S2 Volume:32 Page:S284-S292
ISSN:1060-992X
Container-title:Optical Memory and Neural Networks
language:en
Short-container-title:Opt. Mem. Neural Networks

Author:

Kuderov P.,Dzhivelikian E.,Panov A. I.

Abstract

Abstract For autonomous AI systems, it is important to process spatiotemporal information to encode and memorize it and extract and reuse abstractions effectively. What is natural for natural intelligence is still a challenge for AI systems. In this paper, we propose a biologically plausible model of spatiotemporal memory with an attractor module and study its ability to encode sequences and efficiently extract and reuse repetitive patterns. The results of experiments on synthetic and textual data and data from DVS cameras demonstrate a qualitative improvement in the properties of the model when using the attractor module.

Publisher

Allerton Press

Subject

Electrical and Electronic Engineering,General Computer Science,Electronic, Optical and Magnetic Materials

Link

https://link.springer.com/content/pdf/10.3103/S1060992X23060097.pdf

Reference18 articles.

1. Hafner, D., Pasukonis, J., Ba, J., and Lillicrap, T., Mastering Diverse Domains through World Models. arXiv:2301.04104 [cs, stat]. http://arxiv.org/abs/2301.04104. Accesses January 2023.

2. Sorokin, A., Buzun, N., Pugachev, L., and Burtsev, M., Explain my surprise: Learning efficient long-term memory by predicting uncertain outcomes, Adv. Neural Inf. Process. Syst., 2022, vol. 35, pp. 36875–36888.

3. Rodkin, I., Kuderov, P., and Panov, A.I., Stability and similarity detection for the biologically inspired temporal pooler algorithms, Procedia Comput. Sci., 2022, vol. 213, pp. 570–579.

4. Dzhivelikian, E., Kuderov, P., and Panov, A.I., Learning hidden Markov model of stochastic environment with bio-inspired probabilistic temporal memory, in Procedia Computer Science, 2023.

5. Hochreiter, S. and Schmidhuber, J., Long short-term memory, Neural Comput., 1997, vol. 9, pp. 1735–1780.