no code implementations • 16 Feb 2024 • Alexander Ororbia, Ankur Mali, Adam Kohan, Beren Millidge, Tommaso Salvatori
As a result, it accommodates hardware and scientific modeling, e. g. learning with physical systems and non-differentiable behavior.
no code implementations • 13 Dec 2022 • Adam Kohan, Ed Rietman, Hava Siegelmann
In artificial neural networks, weights are a static representation of synapses.
1 code implementation • 4 Apr 2022 • Adam Kohan, Edward A. Rietman, Hava T. Siegelmann
To further support relevance to biological and hardware learning, we use sigprop to train continuous time neural networks with Hebbian updates, and train spiking neural networks with only the voltage or with biologically and hardware compatible surrogate functions.