Oct 18, 2017 · In this work, we propose sampling-based approximations to weighted function norms as regularizers for deep neural networks.

May 30, 2016 · In this paper, we study the feasibility of directly using the L_2 function norm for regularization. Two methods to integrate this new ...

State-of-the-art training methods, based on weight decay and DropOut, result in impressive performance when a very large training set is available. However, ...

Deep neural networks (DNNs) have had an enormous impact on image analysis. State-of-the-art training methods, based on weight decay and DropOut, result in.

This work provides, to the best of its knowledge, the first proof in the literature of the NP-hardness of computing function norms of DNNs, ...

In this work, we propose sampling-based approximations to weighted function norms as regularizers for deep neural networks. We provide, to the best of our ...

The regularisation terms are 'constraints' by which an optimisation algorithm must 'adhere to' when minimising the loss function, apart from having to minimise ...

We show that matrix completion with trace- norm regularization can be significantly hurt when entries of the matrix are sampled non- uniformly.

Deep neural networks have had an enormous impact on image analysis. State-of- the-art training methods, based on weight decay and DropOut, ...

Oct 28, 2021 · In this study we present a framework for neural network pruning by sampling from a probability function that favors the zeroing of smaller parameters.