Omri Barak

5 papers · 2019–2023 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10)

Venues

NeurIPS (3) ICLR (1) ICML (1)

Top co-authors

Elia Turner (2) Alexis Dubreuil (1) Tie Xu (1) Francesca Mastrogiuseppe (1) Srdjan Ostojic (1) Alexander Rivkind (1) Kabir V Dabholkar (1) Friedrich Schuessler (1) Doron Haviv (1)

Research topics

Deep Learning (5) Architectures (5) Machine Learning (4) Artificial Intelligence (2) Interdisciplinary (2) Core Methods (2) Optimization & Theory (2) Cognitive Science (1) Core AI (1) Learning Paradigms (1) Learning Types (1) Science (1)

Keywords

recurrent neural network (5) dynamical system (2) attractor dynamics (2) gradient descent (1) neural activity (1) low-rank matrices (1) inductive bia (1) random initialization (1) solution space (1) hidden state dynamics (1) cognitive mapping (1) space of solution (1) representation learning (1) task-related behavior (1) reinforcement learning (1) multi-task learning (1)

Papers

The Simplicity Bias in Multi-Task RNNs: Shared Attractors, Reuse of Dynamics, and Geometric Representation NeurIPS 2023 Charting and Navigating the Space of Solutions for Recurrent Neural Networks NeurIPS 2021 Implementing Inductive bias for different navigation tasks through diverse RNN attrractors ICLR 2020 The interplay between randomness and structure during learning in RNNs NeurIPS 2020 Understanding and Controlling Memory in Recurrent Neural Networks ICML 2019