Working memory facilitates reward-modulated Hebbian learning in recurrent neural networks

2019/10/23 by Roman Pogodin, Dane Corneil, Pogodin, Roman +7
Computer Science · Engineering · Neuroscience · #Advanced Memory and Neural Computing #FOS: Biological sciences #FOS: Computer and information sciences #Neural Networks and Reservoir Computing #Neural and Evolutionary Computing (cs.NE) #Neural dynamics and brain function #Neurons and Cognition (q-bio.NC)

paper · pdf · doi:10.48550/arxiv.1910.10559

openalex publication_date 2019/10/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Reservoir computing is a powerful tool to explain how the brain learns temporal sequences, such as movements, but existing learning schemes are either biologically implausible or too inefficient to explain animal performance. We show that a network can learn complicated sequences with a reward-modulated Hebbian learning rule if the network of reservoir neurons is combined with a second network that serves as a dynamic working memory and provides a spatio-temporal backbone signal to the reservoir. In combination with the working memory, reward-modulated Hebbian learning of the readout neurons performs as well as FORCE learning, but with the advantage of a biologically plausible interpretation of both the learning rule and the learning paradigm.

Related

• Training recurrent neural networks with sparse, delayed rewards for flexible decision tasks
• A mathematical analysis of the effects of Hebbian learning rules on the dynamics and structure of discrete-time random recurrent neural networks
• ELiSe: Efficient Learning of Sequences in Structured Recurrent Networks
• Memory-enriched computation and learning in spiking neural networks through Hebbian plasticity
• Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals