1 code implementation • 14 Jul 2023 • Friedrich Schuessler, Francesca Mastrogiuseppe, Srdjan Ostojic, Omri Barak
Here, we utilize recurrent neural networks (RNNs) to explore the question of when and how neural dynamics and the network's output are related from a geometrical point of view.
1 code implementation • NeurIPS 2021 • Elia Turner, Kabir Dabholkar, Omri Barak
Observations in both neuroscience and machine learning challenge this assumption.
no code implementations • 26 Sep 2021 • Aseel Shomar, Omri Barak, Naama Brenner
We review underlying mechanisms that may support this search, and show by using a learning model that such exploratory adaptation is feasible in a high dimensional system as the cell.
1 code implementation • NeurIPS 2020 • Friedrich Schuessler, Francesca Mastrogiuseppe, Alexis Dubreuil, Srdjan Ostojic, Omri Barak
Recurrent neural networks (RNNs) trained on low-dimensional tasks have been widely used to model functional biological networks.
no code implementations • ICLR 2020 • Tie XU, Omri Barak
Navigation is crucial for animal behavior and is assumed to require an internal representation of the external environment, termed a cognitive map.
no code implementations • 22 Jun 2019 • Tomoki Kurikawa, Omri Barak, Kunihiko Kaneko
Memories in neural system are shaped through the interplay of neural and learning dynamics under external inputs.
no code implementations • ICLR 2019 • Doron Haviv, Alexander Rivkind, Omri Barak
To be effective in sequential data processing, Recurrent Neural Networks (RNNs) are required to keep track of past events by creating memories.
2 code implementations • 19 Feb 2019 • Doron Haviv, Alexander Rivkind, Omri Barak
Finally, we propose a novel regularization technique that is based on the relation between hidden state speeds and memory longevity.
no code implementations • 24 May 2018 • Chen Beer, Omri Barak
Our results show that interference between trials can greatly affect learning, in a learning rule dependent manner.