Continual General Chunking Problem and SyncMap

Danilo Vasconcellos Vargas, Toshitake Asabuki

Abstract:

Humans possess an inherent ability to chunk sequences into
their constituent parts. In fact, this ability is thought to boot-
strap 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 struc-
tures and their continual variations. Additionally, we propose
an algorithm called SyncMap1 that can learn and adapt to
changes in the problem by creating a dynamic map which pre-
serves the correlation between variables. Results of SyncMap
suggest that the proposed algorithm learn near optimal solu-
tions, 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.