Kajitsuka, Tokio

1. Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?
   2023/07/26 by Tokio Kajitsuka, Issei Sato, Kajitsuka, Tokio +1 · 6 citations
   Computer Science · Physics and Astronomy · #68T07 #FOS: Computer and information sciences #I.2.0 #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Neural Networks and Applications #Neural Networks and Reservoir Computing
2. On the Optimal Memorization Capacity of Transformers
   2024/09/26 by Tokio Kajitsuka, Issei Sato, Kajitsuka, Tokio +1 · 2 citations
   Computer Science · Engineering · #68T01 #Advanced Memory and Neural Computing #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications