no code implementations • 16 Mar 2021 • Oleksandr Iaroshenko, Andrew T. Sornborger
We use the mechanisms to construct a neuromorphic, binary matrix multiplication algorithm that may be used as a primitive for linear differential equation integration, deep networks, and other standard calculations.
no code implementations • 26 Oct 2017 • Yijing Watkins, Mohammad Sayeh, Oleksandr Iaroshenko, Garrett Kenyon
Bottleneck autoencoders have been actively researched as a solution to image compression tasks.