Hyper Flexible Neural Networks Rapidly Switch between Logic Operations in a Compact Four Neuron Circuit
Authors:
- Alexander James WhiteAWAlexander James White
- Belle LiuBLBelle Liu
- Meng-Fan ChangMCMeng-Fan Chang
- Kuo-An WuKWKuo-An Wu
- Chung-Chuan LoCLChung-Chuan Lo
Preprint
Abstract
Biological neural circuits at various levels exhibit rapid adaptability to diverse environmental stimuli. Such fast response times imply that adaptation cannot rely solely on synaptic plasticity, which operates on a much slower timescale. Instead, circuits must be inherently hyper-flexible and receptive to switches in functionalities without changes in network structure. This biological flexibility is a fruitful mechanism for constructing artificial reconfigurable circuits, whether they are spiking or non-spiking. In this study, we demonstrate that a 4-neuron circuit can rapidly and controllably switch between 24 unique logical functions while maintaining the same set of synaptic weights. Moreover, we show that this reconfigurability works for several different underlying neuronal architectures and strikingly can be applied to a network composed of any sigmoid-shaped activation function. We conclude with proof-of-concept applications showing that we can perform standard tasks such as a full-adder, as well as event-based conditional computing, such as detecting unexpected motion.Keywords
All Related Versions
- Published version: npj Unconventional Computing, 2 (1), 1.
This publication has 62 references indexed in Scilit:
- Network control through coordinated inhibitionCurrent Opinion in Neurobiology, 2021
- Control for multifunctionality: bioinspired control based on feeding in Aplysia californicaBiological Cybernetics, 2020
- Robustness, flexibility, and sensitivity in a multifunctional motor control modelBiological Cybernetics, 2016
- Locomotion and Task Demands Differentially Modulate Thalamic Audiovisual Processing during Active SearchCurrent Biology, 2015
- Beyond the connectome: How neuromodulators shape neural circuitsBioEssays, 2012
- A dynamical systems view of motor preparation2011
- Reservoir computing approaches to recurrent neural network trainingComputer Science Review, 2009
- Weakly Connected Neural Networks1997
- Local Analysis of Weakly Connected Maps1997
- Neural architectures for adaptive behaviorTrends in Neurosciences, 1994