🏢 School of Computing and Data Science, University of Hong Kong
An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models
·2521 words·12 mins·
loading
·
loading
AI Theory
Representation Learning
🏢 School of Computing and Data Science, University of Hong Kong
Deep learning model interpretability improved via Sparse Rate Reduction (SRR), showing improved generalization and offering principled model design.