no code implementations • 7 Sep 2023 • Sama Daryanavard, Bernd Porr
In this work we follow a different approach which is particularly applicable to closed-loop learning of forward models where back-propagation makes exclusive use of the sign of the error signal to prime the learning, whilst a global relevance signal modulates the rate of learning.
no code implementations • 14 Oct 2021 • Sama Daryanavard, Bernd Porr
Standard models of biologically realistic or biologically inspired reinforcement learning employ a global error signal, which implies the use of shallow networks.
1 code implementation • 6 Nov 2020 • Sama Daryanavard, Lucía Muñoz Bohollo, Henry Cowan, Bernd Porr, Ravinder Dahiya
Biological measurements are often contaminated with large amounts of non-stationary noise which require effective noise reduction techniques.
1 code implementation • 9 Jan 2020 • Sama Daryanavard, Bernd Porr
Here, we show how this can be directly achieved by embedding deep learning into a closed loop system and preserving its continuous processing.