Emergence of associative learning in a neuromorphic inference network.

Autor:	Gandolfi D; Department of Biomedical, Metabolic and Neural Sciences, University of Modena and Reggio Emilia, Modena, Italy., Puglisi FM; Department of Engineering 'Enzo Ferrari', University of Modena and Reggio Emilia, Modena, Italy.; Centre for Neuroscience and Neurotechnology, University of Modena and Reggio Emilia, Modena, Italy., Boiani GM; Department of Biomedical, Metabolic and Neural Sciences, University of Modena and Reggio Emilia, Modena, Italy., Pagnoni G; Department of Biomedical, Metabolic and Neural Sciences, University of Modena and Reggio Emilia, Modena, Italy.; Centre for Neuroscience and Neurotechnology, University of Modena and Reggio Emilia, Modena, Italy., Friston KJ; Wellcome Centre for Human Neuroimaging, Institute of Neurology, University College London, 12 Queen Square, London WC1N 3AR, United Kingdom., D'Angelo E; Department of Brain and Behavioral Sciences, University of Pavia, Pavia, Italy.; Brain Connectivity Center, IRCCS Mondino Foundation, Pavia, Italy., Mapelli J; Department of Biomedical, Metabolic and Neural Sciences, University of Modena and Reggio Emilia, Modena, Italy.; Centre for Neuroscience and Neurotechnology, University of Modena and Reggio Emilia, Modena, Italy.
Jazyk:	angličtina
Zdroj:	Journal of neural engineering [J Neural Eng] 2022 May 30; Vol. 19 (3). Date of Electronic Publication: 2022 May 30.
DOI:	10.1088/1741-2552/ac6ca7
Abstrakt:	Objective . In the theoretical framework of predictive coding and active inference, the brain can be viewed as instantiating a rich generative model of the world that predicts incoming sensory data while continuously updating its parameters via minimization of prediction errors. While this theory has been successfully applied to cognitive processes-by modelling the activity of functional neural networks at a mesoscopic scale-the validity of the approach when modelling neurons as an ensemble of inferring agents, in a biologically plausible architecture, remained to be explored. Approach. We modelled a simplified cerebellar circuit with individual neurons acting as Bayesian agents to simulate the classical delayed eyeblink conditioning protocol. Neurons and synapses adjusted their activity to minimize their prediction error, which was used as the network cost function. This cerebellar network was then implemented in hardware by replicating digital neuronal elements via a low-power microcontroller. Main results . Persistent changes of synaptic strength-that mirrored neurophysiological observations-emerged via local (neurocentric) prediction error minimization, leading to the expression of associative learning. The same paradigm was effectively emulated in low-power hardware showing remarkably efficient performance compared to conventional neuromorphic architectures. Significance . These findings show that: (a) an ensemble of free energy minimizing neurons-organized in a biological plausible architecture-can recapitulate functional self-organization observed in nature, such as associative plasticity, and (b) a neuromorphic network of inference units can learn unsupervised tasks without embedding predefined learning rules in the circuit, thus providing a potential avenue to a novel form of brain-inspired artificial intelligence. (Creative Commons Attribution license.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu