1 citations · 1 across the 4 of their papers we have counts for
3 papers · 1 filter
Length-Independent State Tracking Under a Parallel Scan
Julien Brandoit, Arthur Fyon, Thomas Braipson +5
Learning robust and scalable finite-state tracking is fundamental to sequence processing. While linear recurrent neural networks (RNNs), linear attention, and state space models en…
Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications
Julien Brandoit, Arthur Fyon, Damien Ernst +1
Sequence learning is dominated by Transformers and parallelizable recurrent neural networks (RNNs) such as state-space models, yet learning long-term dependencies remains challengi…
Train Short, Act Long: Multistability and the Horizon Independence of Recurrent Policies
Asad Bakija, Florent De Geeter, Julien Brandoit +2
In partially observable reinforcement learning (RL), a decision often depends on a cue seen many steps earlier, and training at such horizons is costly. Ideally, a policy trained o…