返回Google圖書搜尋

Deep Neural Networks are Lazy

其他書名	On the Inductive Bias of Deep Learning
出版	Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
URL	http://books.google.com.hk/books?id=xfruxQEACAAJ&hl=&source=gbs_api

註釋Deep learning models exhibit superior generalization performance despite being heavily overparametrized. Although widely observed in practice, there is currently very little theoretical backing for such a phenomena. In this thesis, we propose a step forward towards understanding generalization in deep learning. We present evidence that deep neural networks have an inherent inductive bias that makes them inclined to learn generalizable hypotheses and avoid memorization. In this respect, we propose results that suggest that the inductive bias stems from neural networks being lazy: they tend to learn simpler rules first. We also propose a definition of simplicity in deep learning based on the implicit priors ingrained in deep neural networks.