Julien Brandoit

Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications

Sequence learning is dominated by Transformers and parallelizable recurrent neural networks such as state-space models, yet learning long-term dependencies remains challenging, and state-of-the-art designs trade power consumption for performance. The Bistable Memory Recurrent Unit (BMRU) was introdu…