Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Dissecting Linear Recurrent Models: How Different Gating Strategies Drive Selectivity and Generalization
Younes Bouhadjar, Maxime Fabre, Felix Schmidt +1
Linear recurrent neural networks have emerged as efficient alternatives to the original Transformer's softmax attention mechanism, thanks to their highly parallelizable training an…
cs.LG2023
Unlocking Layer-wise Relevance Propagation for Autoencoders
Kenyu Kobayashi, Renata Khasanova, Arno Schneuwly +2
Autoencoders are a powerful and versatile tool often used for various problems such as anomaly detection, image processing and machine translation. However, their reconstructions a…