On sample complexity of neural networks

10/24/2019

∙

We consider functions defined by deep neural networks as definable objects in an o-miminal expansion of the real field, and derive an almost linear (in the number of weights) bound on sample complexity of such networks.

READ FULL TEXT

On sample complexity of neural networks

Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks

On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences

On the Study of Sample Complexity for Polynomial Neural Networks

On the Sample Complexity of Learning from a Sequence of Experiments

On the Sample Complexity of Super-Resolution Radar

Automata Cascades: Expressivity and Sample Complexity

Sample Complexity Result for Multi-category Classifiers of Bounded Variation

On sample complexity of neural networks

Related Research

Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks

On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences

On the Study of Sample Complexity for Polynomial Neural Networks

On the Sample Complexity of Learning from a Sequence of Experiments

On the Sample Complexity of Super-Resolution Radar

Automata Cascades: Expressivity and Sample Complexity

Sample Complexity Result for Multi-category Classifiers of Bounded Variation