The remarkable performance of deep Convolutional neural networks (CNNs) is generally
attributed to their deeper and wider architectures, which can come with significant …

In this paper, we provide a systematic approach for assessing and comparing the
computational complexity of neural network layers in digital signal processing. We provide …

This chapter provides approaches to the problem of quantizing the numerical values in deep
Neural Network computations, covering the advantages/disadvantages of current methods …

While neural networks have advanced the frontiers in many applications, they often come at
a high computational cost. Reducing the power and latency of neural network inference is …

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 …

Current low-precision quantization algorithms often have the hidden cost of conversion back
and forth from floating point to quantized integer values. This hidden cost limits the latency …

Neural network pruning and quantization techniques are almost as old as neural networks
themselves. However, to date, only ad-hoc comparisons between the two have been …

We propose a new simple approach for image compression: instead of storing the RGB
values for each pixel of an image, we store the weights of a neural network overfitted to the …

Transformer-based architectures have become the de-facto standard models for a wide
range of Natural Language Processing tasks. However, their memory footprint and high …

Structured pruning is a commonly used technique in deploying deep neural networks
(DNNs) onto resource-constrained devices. However, the existing pruning methods are …