A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks 论文
2017International Conference on Learning Representations引用 256
Neural Networks and ApplicationsFault Detection and Control SystemsAdvanced Neural Network Applications
摘要
We present a generalization bound for feedforward neural networks in terms of the product of the spectral norm of the layers and the Frobenius norm of the weights. The generalization bound is derived using a PAC-Bayes analysis.