2 papers
cs.NE2024
Using evolutionary computation to optimize task performance of unclocked, recurrent Boolean circuits in FPGAs
Raphael Norman-Tenazas, David Kleinberg, Erik C. Johnson +2
It has been shown that unclocked, recurrent networks of Boolean gates in FPGAs can be used for low-SWaP reservoir computing. In such systems, topology and node functionality of the…
cs.NE2023
Exploiting Large Neuroimaging Datasets to Create Connectome-Constrained Approaches for more Robust, Efficient, and Adaptable Artificial Intelligence
Erik C. Johnson, Brian S. Robinson, Gautam K. Vallabha +17
Despite the progress in deep learning networks, efficient learning at the edge (enabling adaptable, low-complexity machine learning solutions) remains a critical need for defense a…