AI RESEARCH

Fast weight programming and linear transformers: from machine learning to neurobiology

arXiv CS.LG

ArXi:2508.08435v5 Announce Type: replace Recent advances in artificial neural networks for machine learning, and language modeling in particular, have established a family of recurrent neural network (RNN) architectures that, unlike conventional RNNs with vector-form hidden states, use two-dimensional (2D) matrix-form hidden states.