Fast weight programming and linear transformers: from machine learning to neurobiology
Fast weight programming and linear transformers: from machine learning to neurobiology
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. Such 2D-state RNNs, known as Fast Weight Programmers (FWPs), can be interpreted as a neural network whose synaptic weights (called fast weights) dynamically change over time as a function of input observations, and serve as short-term memory storage; corresponding synaptic weight modifications are controlled or programmed by another network (the programmer) whose parameters are trained (e.g., by gradient descent). In this Primer, we review the technical foundations of FWPs, their computational characteristics, and their connections to transformers and state space models. We also discuss connections between FWPs and models of synaptic plasticity in the brain, suggesting a convergence of natural and artificial intelligence.
Kazuki Irie、Samuel J. Gershman
计算技术、计算机技术生物科学理论、生物科学方法
Kazuki Irie,Samuel J. Gershman.Fast weight programming and linear transformers: from machine learning to neurobiology[EB/OL].(2025-08-11)[2025-08-24].https://arxiv.org/abs/2508.08435.点此复制
评论