Large Language Models (LLMs) have recently demonstrated remarkable capabilities in
natural language processing tasks and beyond. This success of LLMs has led to a large …

Domain-specific hardware is becoming a promising topic in the backdrop of improvement
slow down for general-purpose processors due to the foreseeable end of Moore's Law …

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

Quantization is one of the most effective methods to compress neural networks, which has
achieved great success on convolutional neural networks (CNNs). Recently, vision …

The recent advancements in self-supervised learning, combined with the Transformer
architecture, have enabled natural language processing (NLP) to achieve remarkably low …

Deep neural networks enable state-of-the-art accuracy on visual recognition tasks such as
image classification and object detection. However, modern deep networks contain millions …

Lightweight deep convolutional neural networks (LDCNNs) are vital components of mobile
intelligence, particularly in mobile vision. Although various heavy networks with increasingly …

Deep neural networks are the state-of-the-art methods for many real-world tasks, such as
computer vision, natural language processing and speech recognition. For all its popularity …

In recent years, the fields of natural language processing (NLP) and information retrieval (IR)
have made tremendous progress thanks to deep learning models like Recurrent Neural …

In this paper, we propose to train convolutional neural networks (CNNs) with both binarized
weights and activations, leading to quantized models specifically for mobile devices with …