Description
Residual Shuffle-Exchange Network is an efficient alternative to models using an attention mechanism that allows the modelling of long-range dependencies in sequences in O(n log n) time. This model achieved state-of-the-art performance on the MusicNet dataset for music transcription while being able to run inference on a single GPU fast enough to be suitable for real-time audio processing.
Papers Using This Method
Nash Equilibrium Between Consumer Electronic Devices and DoS Attacker for Distributed IoT-enabled RSE Systems2025-04-13The radius of statistical efficiency2024-05-15A Multi-Modal Machine Learning Approach to Detect Extreme Rainfall Events in Sicily2022-12-14Attack-Resilient State Estimation with Intermittent Data Authentication2020-05-16Residual Shuffle-Exchange Networks for Fast Processing of Long Sequences2020-04-06