This paper reviews the current state of the art in artificial intelligence (AI) technologies and
applications in the context of the creative industries. A brief background of AI, and …

The research advances concerning the typical architectures of convolutional neural
networks (CNNs) as well as their optimizations are analyzed and elaborated in detail in this …

We study the challenging task of neural network quantization without end-to-end retraining,
called Post-training Quantization (PTQ). PTQ usually requires a small subset of training data …

During typical gradient-based training of deep neural networks, all of the model's
parameters are updated at each iteration. Recent work has shown that it is possible to …

Structural pruning of neural network parameters reduces computational, energy, and
memory transfer costs during inference. We propose a novel method that estimates the …

Neural Architecture Search (NAS) is quickly becoming the standard methodology to design
neural network models. However, NAS is typically compute-intensive because multiple …

Magnitude pruning is a widely used strategy for reducing model size in pure supervised
learning; however, it is less effective in the transfer learning regime that has become …

In the past decade, advances in deep learning have resulted in breakthroughs in a variety of
areas, including computer vision, natural language understanding, speech recognition, and …

Pruning is an effective way to reduce the huge inference cost of Transformer models.
However, prior work on pruning Transformers requires retraining the models. This can add …

We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural
networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to …