Real time unsupervised learning of visual stimuli in neuromorphic VLSI systems

TL;DR

This paper demonstrates real-time, unsupervised learning of visual stimuli in neuromorphic VLSI systems by leveraging attractor dynamics in recurrent spiking neural networks, enabling autonomous development of stimulus-specific associative memory.

Contribution

It introduces a theory-driven approach to on-chip synaptic plasticity that autonomously learns stimulus-specific attractors without separate learning and retrieval phases.

Findings

Synaptic plasticity shapes stimulus-specific attractor states.

Associative memory forms through coupled neural activity and synaptic dynamics.

Learning occurs autonomously during stimulus presentation.

Abstract

Neuromorphic chips embody computational principles operating in the nervous system, into microelectronic devices. In this domain it is important to identify computational primitives that theory and experiments suggest as generic and reusable cognitive elements. One such element is provided by attractor dynamics in recurrent networks. Point attractors are equilibrium states of the dynamics (up to fluctuations), determined by the synaptic structure of the network; a `basin' of attraction comprises all initial states leading to a given attractor upon relaxation, hence making attractor dynamics suitable to implement robust associative memory. The initial network state is dictated by the stimulus, and relaxation to the attractor state implements the retrieval of the corresponding memorized prototypical pattern. In a previous work we demonstrated that a neuromorphic recurrent network of spiking neurons and suitably chosen, fixed synapses supports attractor dynamics. Here we focus on learning: activating on-chip synaptic plasticity and using a theory-driven strategy for choosing network parameters, we show that autonomous learning, following repeated presentation of simple visual stimuli, shapes a synaptic connectivity supporting stimulus-selective attractors. Associative memory develops on chip as the result of the coupled stimulus-driven neural activity and ensuing synaptic dynamics, with no artificial separation between learning and retrieval phases.