INFERNO: A Novel Architecture for Generating Long Neuronal Sequences with Spikes

Alex Pitti (1) , Philippe Gaussier (1) , Mathias Quoy (1)

1 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes

Human working memory is capable to generate dynamically robust and flexible neuronal sequences for action planning, problem solving and decision making. However, current neurocomputational models of working memory find hard to achieve these capabilities since intrinsic noise is difficult to stabilize over time and destroys global synchrony. As part of the principle of free-energy minimization proposed by Karl Fris-ton, we propose a novel neural architecture to optimize the free-energy inherent to spiking recurrent neural networks to regulate their activity. We show for the first time that it is possible to stabilize iteratively the long-range control of a recurrent spiking neurons network over long sequences. We identify our architecture as the working memory composed by the Basal Ganglia and the Intra-Parietal Lobe for action selection and we make some comparisons with other networks such as deep neural networks and neural Turing machines. We name our architecture INFERNO for Iterative Free-Energy Optimization for Recurrent Neural Network.

Mots clés: Free-Energy; Predictive Coding; Working Memory; Neuronal Sequences; Spiking neurons; STDP; Basal Ganglia; Cortico-basal; Loops; Habit Learning

Domaines: Robotique [cs.RO]

Alex Pitti, Philippe Gaussier, Mathias Quoy. INFERNO: A Novel Architecture for Generating Long Neuronal Sequences with Spikes. 14th International Symposium, ISNN 2017, Sapporo, Hakodate, and Muroran, Hokkaido, Japan, June 21–26, 2017, Proceedings, Part I, Jun 2017, Sapporo, Japan. pp.421-428, ⟨10.1007/978-3-319-59072-1_50⟩. ⟨hal-01609619⟩