Representational Drift in Neural Networks: What Backpropagation and Hebbian Learning Reveal
中文摘要
该研究通过对比反向传播与赫布学习，揭示了神经网络内部表示随时间发生漂移的原因。
English Summary
This study compares backpropagation and Hebbian learning to explain why neural networks experience representational drift over time.
Original Excerpt
An experiment comparing backpropagation and Hebbian learning shows why a neural network’s internal representations keep changing long… Continue reading on Towards AI »