Multifunctionality in a Connectome-Based Reservoir Computer
This work addresses the challenge of multifunctionality in reservoir computing, which is incremental as it applies an existing biological connectome to a known machine learning paradigm.
The authors tackled the problem of enabling neural networks to perform multiple tasks without changing connections by transplanting the fruit fly lateral horn connectome into a reservoir computer, resulting in greater multifunctionality capacity, broader hyperparameter range, and solving the 'seeing double' problem beyond previous spectral radius limits compared to an Erdös-Renyi reservoir computer.
Multifunctionality describes the capacity for a neural network to perform multiple mutually exclusive tasks without altering its network connections; and is an emerging area of interest in the reservoir computing machine learning paradigm. Multifunctionality has been observed in the brains of humans and other animals: particularly, in the lateral horn of the fruit fly. In this work, we transplant the connectome of the fruit fly lateral horn to a reservoir computer (RC), and investigate the extent to which this 'fruit fly RC' (FFRC) exhibits multifunctionality using the 'seeing double' problem as a benchmark test. We furthermore explore the dynamics of how this FFRC achieves multifunctionality while varying the network's spectral radius. Compared to the widely-used Erdös-Renyi Reservoir Computer (ERRC), we report that the FFRC exhibits a greater capacity for multifunctionality; is multifunctional across a broader hyperparameter range; and solves the seeing double problem far beyond the previously observed spectral radius limit, wherein the ERRC's dynamics become chaotic.