Brain-like learning with exponentiated gradients
Jonathan Cornford, Roman Pogodin, Arna Ghosh, Kaiwen Sheng, Brendan Bicknell, Oliver Codol, Beverly Clark, Guillaume Lajoie, Blake Richards · COSYNE 2025
Computational neuroscience increasingly leverages gradient descent (GD) for training artificial neural network (ANN) models of the brain. GD’s advantage is that it is very effective at learning difficult tasks. This is important for the role of computational models as the interface between theory and empirical data (Levenstein et al., 2023), since models that can learn realistic tasks from realistic, high-dimensional inputs can be more directly compared to experimental data (Doerig et al., 2023). However, GD produces ANNs that are poor phenomenological fits to biology, making them less relevan
ePoster · Neuroscience