Emergent Computations in Trained Artificial Neural Networks and Real Brains

Abstract

Synaptic plasticity allows cortical circuits to learn new tasks and to adapt to changing environments. How do cortical circuits use plasticity to acquire functions such as decision-making or working memory? Neurons are connected in complex ways, forming recurrent neural networks, and learning modifies the strength of their connections. Moreover, neurons communicate emitting brief discrete electric signals. Here we describe how to train recurrent neural networks in tasks like those used to train animals in neuroscience laboratories, and how computations emerge in the trained networks. Surprisingly, artificial networks and real brains can use similar computational strategies.

arXiv commentInternational Summer School on Intelligent Signal Processing for Frontier Research and Industry, INFIERI 2021. Universidad Autónoma de Madrid, Madrid, Spain. 23 August - 4 September 2021

References in corpus (10)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Complexity without chaos: Plasticity within random recurrent networks generates robust timing and motor control
• Stimulus-Dependent Suppression of Chaos in Recurrent Neural Networks
• Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rules
• Supervised Learning in Spiking Neural Networks with FORCE Training
• full-FORCE: A Target-Based Method for Training Recurrent Networks
• Gradient learning in spiking neural networks by dynamic perturbation of conductances
• Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes
• How humans learn and represent networks
• Using Firing-Rate Dynamics to Train Recurrent Networks of Spiking Model Neurons

Cited by in corpus (1)

• End-to-end Stroke imaging analysis, using reservoir computing-based effective connectivity, and interpretable Artificial intelligence