Litcius/Paper detail

Complexity control by gradient descent in deep networks

Tomaso Poggio, Qianli Liao, Andrzej Banburski

2020Nature Communications34 citationsDOIOpen Access PDF

Abstract

Overparametrized deep networks predict well, despite the lack of an explicit complexity control during training, such as an explicit regularization term. For exponential-type loss functions, we solve this puzzle by showing an effective regularization effect of gradient descent in terms of the normalized weights that are relevant for classification.

Topics & Concepts

Gradient descentRegularization (linguistics)Computer scienceExponential functionStochastic gradient descentDeep learningArtificial intelligenceAlgorithmApplied mathematicsMathematicsArtificial neural networkMathematical analysisBlind Source Separation TechniquesNeural Networks and ApplicationsMachine Learning and ELM
Complexity control by gradient descent in deep networks | Litcius