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 …

Neural networks tend to achieve better accuracy with training if they are larger {—} even if
the resulting models are overparameterized. Nevertheless, carefully removing such excess …

Filter pruning is effective to reduce the computational costs of neural networks. Existing
methods show that updating the previous pruned filter would enable large model capacity …

To deploy machine learning models on-device, practitioners use compression algorithms to
shrink and speed up models while maintaining their high-quality output. A critical aspect of …

Pruning can remove the redundant parameters and structures of Deep Neural Networks
(DNNs) to reduce inference time and memory overhead. As one of the important …

We can compress a rectifier network while exactly preserving its underlying functionality with
respect to a given input domain if some of its neurons are stable. However, current …

The incorporation of renewable energy sources into the power grid has necessitated the
development of sophisticated forecasting models that can effectively handle the inherent …

Despite the remarkable performance, modern deep neural networks are inevitably
accompanied by a significant amount of computational cost for learning and deployment …

Learned iterative shrinkage thresholding algorithm (LISTA), which adopts deep learning
techniques to optimize algorithm parameters from labeled training data, can be successfully …

We present a computationally efficient method for compressing a trained neural network
without using real data. We break the problem of data-free network compression into …