Continual General Chunking Problem and SyncMap

Authors

  • Danilo Vasconcellos Vargas Kyushu University The University of Tokyo
  • Toshitake Asabuki Okinawa Institute of Science and Technology Graduate University

Keywords:

Bio-inspired Learning, Simulating Humans, Geometric, Spatial, and Temporal Reasoning, Unsupervised & Self-Supervised Learning

Abstract

Humans possess an inherent ability to chunk sequences into their constituent parts. In fact, this ability is thought to bootstrap language skills and learning of image patterns which might be a key to a more animal-like type of intelligence. Here, we propose a continual generalization of the chunking problem (an unsupervised problem), encompassing fixed and probabilistic chunks, discovery of temporal and causal structures and their continual variations. Additionally, we propose an algorithm called SyncMap that can learn and adapt to changes in the problem by creating a dynamic map which preserves the correlation between variables. Results of SyncMap suggest that the proposed algorithm learn near optimal solutions, despite the presence of many types of structures and their continual variation. When compared to Word2vec, PARSER and MRIL, SyncMap surpasses or ties with the best algorithm on 66% of the scenarios while being the second best in the remaining 34%. SyncMap's model-free simple dynamics and the absence of loss functions reveal that, perhaps surprisingly, much can be done with self-organization alone.

Downloads

Published

2021-05-18

How to Cite

Vasconcellos Vargas, D., & Asabuki, T. (2021). Continual General Chunking Problem and SyncMap. Proceedings of the AAAI Conference on Artificial Intelligence, 35(11), 10006-10014. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17201

Issue

Section

AAAI Technical Track on Machine Learning IV