The growing energy and performance costs of deep learning have driven the community to
reduce the size of neural networks by selectively pruning components. Similarly to their …

To reduce the significant redundancy in deep Convolutional Neural Networks (CNNs), most
existing methods prune neurons by only considering the statistics of an individual layer or …

Deep convolutional neural networks have liberated its extraordinary power on various tasks.
However, it is still very challenging to deploy state-of-the-art models into real-world …

Deep Neural Networks (DNNs) are typically trained by backpropagation in a batch learning
setting, which requires the entire training data to be made available prior to the learning …

The emergence of Deep neural networks has seen human-level performance on large scale
computer vision tasks such as image classification. However these deep networks typically …

Deep convolutional neural networks (CNNs) have demonstrated its extraordinary power on
various visual tasks like object detection and classification. However, it is still challenging to …

A DNN-based surrogate for turbulence (and transition) closure of the Reynolds-Averaged
Navier–Stokes (RANS) equations is presented. The DNN configuration, namely the …

Important applications such as mobile computing require reducing the computational costs
of neural network inference. Ideally, applications would specify their preferred tradeoff …

In this work, we propose a heuristic genetic algorithm (GA) for pruning convolutional neural
networks (CNNs) according to the multi-objective trade-off among error, computation and …

Deep Neural Networks often require good regularizers to generalize well. Dropout is one
such regularizer that is widely used among Deep Learning practitioners. Recent work has …