no code implementations • 13 Jul 2023 • Vicky Zhu, Robert Rosenbaum
A natural approach is to use gradient descent on the Euclidean space of synaptic weights.
1 code implementation • 28 Oct 2022 • Navid Shervani-Tabar, Robert Rosenbaum
In this study, we develop a meta-learning approach to discover interpretable, biologically plausible plasticity rules that improve online learning performance with fixed random feedback connections.
1 code implementation • 3 Feb 2022 • Vicky Zhu, Robert Rosenbaum
Homeostatic inhibitory synaptic plasticity is a promising mechanism for training neuronal networks to perform predictive coding.
2 code implementations • 20 Jun 2021 • Robert Rosenbaum
Artificial neural networks are often interpreted as abstract models of biological neuronal networks, but they are typically trained using the biologically unrealistic backpropagation algorithm and its variants.
no code implementations • 8 Mar 2018 • Ryan Pyle, Robert Rosenbaum
Many recent studies of the motor system are divided into two distinct approaches: Those that investigate how motor responses are encoded in cortical neurons' firing rate dynamics and those that study the learning rules by which mammals and songbirds develop reliable motor responses.