Understanding deep learning requires rethinking generalization Conventional wisdom attributes small generalization error either to properties of the model family, or to the regularization techniques used during training Through extensive systematic experiments, we show how these traditional approaches fail to explain why large neural networks generalize well in practice
Understanding deep learning requires rethinking generalization Through extensive systematic experiments, we show how the traditional approaches fail to explain why large neural networks generalize well in practice, and why understanding deep learning requires rethinking generalization
Understanding deep learning requires rethinking generalization Although deep neural nets remain mysterious for many reasons, we note in this section that it is not necessarily easy to understand the source of generalization for linear models either