GUST: Combinatorial Generalization by Unsupervised Grouping with Neuronal Coherence

Published: 21 Sept 2023, Last Modified: 05 Jan 2024NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: neuronal coherence, combinatorial generalization, perceptual grouping, unsupervised learning
TL;DR: grouping with emergent synchronization and the representation can generalize combinatorially
Abstract: Dynamically grouping sensory information into structured entities is essential for understanding the world of combinatorial nature. However, the grouping ability and therefore combinatorial generalization are still challenging artificial neural networks. Inspired by the evidence that successful grouping is indicated by neuronal coherence in the human brain, we introduce GUST (Grouping Unsupervisely by Spike Timing network), an iterative network architecture with biological constraints to bias the network towards a dynamical state of neuronal coherence that softly reflects the grouping information in the temporal structure of its spiking activity. We evaluate and analyze the model on synthetic datasets. Interestingly, the segregation ability is directly learned from superimposed stimuli with a succinct unsupervised objective. Two learning stages are present, from coarsely perceiving global features to additionally capturing local features. Further, the learned symbol-like building blocks can be systematically composed to represent novel scenes in a bio-plausible manner.
Supplementary Material: pdf
Submission Number: 6645