Neural Classifiers as Error-Correcting Codeswith Sergey Salishev, Anton Makarov, Oleg Granichin, Renata Avros1 versionW_bvdvgvusv1 · current
Transformers as Generic Deep Neural Networks: Exact Compilation, the Cost of Removing Activation-Activation Products, and Multi-Agent Attention ClusteringW_6mjg35w8v1
Transformers as Generic Deep Neural Networks: Exact Compilation, the Cost of Removing Activation-Activation Products, and Multi-Agent Attention ClusteringSergey Salishev, Zeev Volkovich, Oleg Granichin0 citations2610.28958v12026arXivon Valency