Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attention

TL;DR

This paper introduces a hybrid neural network combining spike timing dynamics and reconstructive attention to address the binding problem, enabling better object grouping and compositional understanding in artificial neural networks.

Contribution

The paper proposes a novel brain-inspired hybrid neural network integrating SNNs and ANNs, demonstrating improved binding and generalization without explicit supervision.

Findings

Successfully binds multiple objects in synthetic datasets

Demonstrates explainable and hierarchical binding behavior

Shows compositional generalization in dynamic scenarios

Abstract

The binding problem is one of the fundamental challenges that prevent the artificial neural network (ANNs) from a compositional understanding of the world like human perception, because disentangled and distributed representations of generative factors can interfere and lead to ambiguity when complex data with multiple objects are presented. In this paper, we propose a brain-inspired hybrid neural network (HNN) that introduces temporal binding theory originated from neuroscience into ANNs by integrating spike timing dynamics (via spiking neural networks, SNNs) with reconstructive attention (by ANNs). Spike timing provides an additional dimension for grouping, while reconstructive feedback coordinates the spikes into temporal coherent states. Through iterative interaction of ANN and SNN, the model continuously binds multiple objects at alternative synchronous firing times in the SNN coding space. The effectiveness of the model is evaluated on synthetic datasets of binary images. By visualization and analysis, we demonstrate that the binding is explainable, soft, flexible, and hierarchical. Notably, the model is trained on single object datasets without explicit supervision on grouping, but successfully binds multiple objects on test datasets, showing its compositional generalization capability. Further results show its binding ability in dynamic situations.