Extreme neural machines

• Published in: Neural networks Vol. 144; pp. 639 - 647
• Main Authors: Boucher-Routhier, Megan, Zhang, Bill Ling Feng, Thivierge, Jean-Philippe
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.12.2021
• Subjects: Extreme learning machines; Image processing; Recurrent network; Spiking neurons; Temporal sequences; Visual cortex; Visual cortex; Spiking neurons; Extreme learning machines; Temporal sequences; Image processing; Recurrent network
• ISSN: 0893-6080; 1879-2782
• DOI: 10.1016/j.neunet.2021.09.021

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. •We developed a one-shot learning rule to train biologically-realistic recurrent networks.•The model learned to faithfully reproduce both static images and sequential patterns.•Results open the path to rapid learning in brain-like networks.