Continual General Chunking Problem and SyncMap
This addresses the problem of continual learning and structure discovery in sequences for AI systems aiming to mimic human-like intelligence, though it appears incremental in extending chunking to continual variations.
The paper tackles the continual generalization of the chunking problem, an unsupervised task involving temporal and causal structures, by proposing the SyncMap algorithm, which learns near-optimal solutions and outperforms or ties with best algorithms like Word2vec, PARSER, and MRIL in 66% of scenarios.
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. Code available at https://github.com/zweifel/SyncMap.