Extreme neural machines.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

Recurrent neural networks can solve a variety of computational tasks and produce patterns of activity that capture key properties of brain circuits. However, learning rules designed to train these models are time-consuming and prone to inaccuracies when tuning connection weights located deep within the network. Here, we describe a rapid one-shot learning rule to train recurrent networks composed of biologically-grounded neurons. First, inputs to the model are compressed onto a smaller number of recurrent neurons. Then, a non-iterative rule adjusts the output weights of these neurons based on a target signal. The model learned to reproduce natural images, sequential patterns, as well as a high-resolution movie scene. Together, results provide a novel avenue for one-shot learning in biologically realistic recurrent networks and open a path to solving complex tasks by merging brain-inspired models with rapid optimization rules.

Authors

  • Megan Boucher-Routhier
    School of Psychology, University of Ottawa, Ontario, Canada K1N 6N5. Electronic address: mrout092@uottawa.ca.
  • Bill Ling Feng Zhang
    Department of Biology, University of Ottawa, Ontario, Canada K1N 6N5. Electronic address: bzhan117@uottawa.ca.
  • Jean-Philippe Thivierge
    School of Psychology and Center for Neural Dynamics, University of Ottawa, Ottawa, Ontario, Canada.