Concept transfer of synaptic diversity from biological to artificial neural networks.

Journal: Nature communications
Published Date:

Abstract

Recent developments in artificial neural networks have drawn inspiration from biological neural networks, leveraging the concept of the artificial neuron to model the learning abilities of biological nerve cells. However, while neuroscience has provided new insights into the mechanisms of biological neural networks, only a limited number of these concepts have been directly applied to artificial neural networks, with no guarantee of improved performance. Here, we address the discrepancy between the inhomogeneous and dynamic structures of biological neural networks and the largely homogeneous and fixed topologies of artificial neural networks. Specifically, we demonstrate successful integration of concepts of synaptic diversity, including spontaneous spine remodeling, synaptic plasticity diversity, and multi-synaptic connectivity, into artificial neural networks. Our findings reveal increased learning speed, prediction accuracy, and resilience to gradient inversion attacks. Our publicly available drop-in replacement code enables easy incorporation of these proposed concepts into existing networks.

Authors

  • Martin Hofmann
    Department of Urology, Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA; Department of Urology, University of California, Irvine, CA, USA.
  • Moritz Franz Peter Becker
    Group of Computational Synaptic Physiology, Department for Neuro- and Sensory Physiology, University Medical Center Göttingen, Humboldtallee 23, Göttingen, 37073, Lower Saxony, Germany.
  • Christian Tetzlaff
    Third Institute of Physics, Universität Göttingen, Friedrich-Hund Platz 1, 37077 Göttingen, Germany; Bernstein Center for Computational Neuroscience, Friedrich-Hund Platz 1, 37077 Göttingen, Germany.
  • Patrick Mäder
    Software Engineering for Safety-Critical Systems Group, Technische Universität Ilmenau, Ehrenbergstraße 29, 98693, Ilmenau, Germany.