Informing deep neural networks by multiscale principles of neuromodulatory systems.

Journal: Trends in neurosciences
Published Date:

Abstract

Our brains have evolved the ability to configure and adapt their processing states to match the unique challenges of acting and learning in diverse environments and behavioral contexts. In biological nervous systems, such state specification and adaptation arise in part from neuromodulators, including acetylcholine, noradrenaline, serotonin, and dopamine, whose diffuse release fine-tunes neuronal and synaptic dynamics and plasticity to complement the behavioral context in real-time. Despite the demonstrated effectiveness of deep neural networks for specific tasks, they remain relatively inflexible at generalizing across tasks or adapting to ever-changing behavioral demands. In this article, we provide an overview of neuromodulatory systems and their relationship to emerging pertinent principles in deep neural networks. We further outline opportunities for the integration of neuromodulatory principles into deep neural networks, towards endowing artificial intelligence with a key ingredient underlying the flexibility and learning capability of biological systems.

Authors

  • Jie Mei
    Department of Neurology and Department of Experimental Neurology, Neurocure Cluster of Excellence, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin, Humboldt Universität zu Berlin, and Berlin Institute of Health, Berlin, Germany.
  • Eilif Muller
    Blue Brain Project, Ecole Polytechnique Fédérale de Lausanne (EPFL), CH-1015, Lausanne, Switzerland.
  • Srikanth Ramaswamy
    Institute of Physiology, University of Bern, Switzerland; Biosciences Institute, Newcastle University, UK. Electronic address: srikanth.ramaswamy@newcastle.ac.uk.