1 code implementation • 2 Jun 2022 • Yuhan Helena Liu, Stephen Smith, Stefan Mihalas, Eric Shea-Brown, Uygar Sümbül
Finally, we derive an in-silico implementation of ModProp that could serve as a low-complexity and causal alternative to backpropagation through time.
no code implementations • NeurIPS Workshop Neuro_AI 2019 • Brian Hu, Jiaqi Shang, Ramakrishnan Iyer, Josh Siegle, Stefan Mihalas
Neural activity is highly variable in response to repeated stimuli.
no code implementations • NeurIPS Workshop Neuro_AI 2019 • Brian Hu, Stefan Mihalas
To address these issues, we combine traditional supervised learning via backpropagation with a specialized unsupervised learning rule to learn lateral connections between neurons within a convolutional neural network.
1 code implementation • NeurIPS 2016 • Kameron Decker Harris, Stefan Mihalas, Eric Shea-Brown
We demonstrate the efficacy of a low rank version on visual cortex data and discuss the possibility of extending this to a whole-brain connectivity matrix at the voxel scale.