Context Modulation Enables Multi-tasking and Resource Efficiency in Liquid State Machines

Date
2023-08-28
Authors
Helfer, Peter
Teeter, Corinne
Hill, Aaron
Vineyard, Craig M.
Aimone, James B.
Kudithipudi, Dhireesha
Journal Title
Journal ISSN
Volume Title
Publisher
Association for Computing Machinery
Abstract

Memory storage and retrieval are context-sensitive in both humans and animals; memories are more accurately retrieved in the context where they were acquired, and similar stimuli can elicit different responses in different contexts. Researchers have suggested that such effects may be underpinned by mechanisms that modulate the dynamics of neural circuits in a context-dependent fashion. Based on this idea, we design a mechanism for context-dependent modulation of a liquid state machine, a recurrent spiking artificial neural network. We find that context modulation enables a single network to multitask and requires fewer neurons than when several smaller networks are used to perform the tasks individually.

Description
Keywords
context modulation, neuromorphic, spiking neural network, liquid state machine
Citation
Helfer, P., Teeter, C., Hill, A., Vineyard, C. M., Aimone, J. B., & Kudithipudi, D. (2023). Context Modulation Enables Multi-tasking and Resource Efficiency in Liquid State Machines. Paper presented at the 2023 International Conference on Neuromorphic Systems, Santa Fe, NM, USA. https://doi.org/10.1145/3589737.3605975
Department
Electrical and Computer Engineering
Computer Science