EventSession Formset ID 363

Event: ccnw24 2024
Type: Discussion
Title: Fully local learning through space and time

In the brain, synaptic learning is constrained to use spatio-temporal local information. However, the majority of the learning algorithms that we use to train neural networks violate spatial or temporal locality (such as RTRL and BPTT).

How can the brain efficiently assign credit using only local spatio-temporal information?

In this discussion group, we aim to explore biologically plausible solutions to the spatio-temporal credit assignment problem. Additionally, I will introduce our computational framework (GLE) for fully local spatio-temporal credit assignment in physical, dynamical networks of neurons. This framework approximates BPTT in deep cortical networks with continuous-time neuronal dynamics and continuously active, local synaptic plasticity.

Ellenberger, B., Haider, P., Jordan, J., Max, K., Jaras, I., Kriener, L., Benitez, F., & Petrovici, M.A. (2024). Backpropagation through space, time, and the brain. ArXiv, abs/2403.16933.

Speaker: Ismael Jaras,
Schedule ID start time end time location
453 May 03 2024, 16:00 May 03 2024, 18:00 Panorama
List all sessions Update Delete