Related papers: DANCE: Differentiable Accelerator/Network Co-Explo…

An accelerator is a specialized integrated circuit designed to perform specific computations faster than if those were performed by CPU or GPU. A Field-Programmable DNN learning and inference accelerator (FProg-DNN) using hybrid systolic…

Deep neural networks (DNNs) have been increasingly deployed on and integrated with edge devices, such as mobile phones, drones, robots and wearables. To run DNN inference directly on edge devices (a.k.a. edge inference) with a satisfactory…

Recent breakthroughs in Deep Learning (DL) applications have made DL models a key component in almost every modern computing system. The increased popularity of DL applications deployed on a wide-spectrum of platforms have resulted in a…

Recently, Neural Architecture Search (NAS) methods are introduced and show impressive performance on many benchmarks. Among those NAS studies, Neural Architecture Transformer (NAT) aims to improve the given neural architecture to have…

Deep neural networks (DNN) have demonstrated effectiveness for various applications such as image processing, video segmentation, and speech recognition. Running state-of-the-art DNNs on current systems mostly relies on either…

Graph neural networks (GNNs) have shown significant accuracy improvements in a variety of graph learning domains, sparking considerable research interest. To translate these accuracy improvements into practical applications, it is essential…

In deep learning applications, the architectures of deep neural networks are crucial in achieving high accuracy. Many methods have been proposed to search for high-performance neural architectures automatically. However, these searched…

With the rapid development of neural architecture search (NAS), researchers found powerful network architectures for a wide range of vision tasks. However, it remains unclear if the searched architecture can transfer across different types…

In this paper, we propose a Distributed Accumulated Newton Conjugate gradiEnt (DANCE) method in which sample size is gradually increasing to quickly obtain a solution whose empirical loss is under satisfactory statistical accuracy. Our…

This paper studies the neural architecture search (NAS) problem for developing efficient generator networks. Compared with deep models for visual recognition tasks, generative adversarial network (GAN) are usually designed to conduct…

Hardware-Software Co-Design is a highly successful strategy for improving performance of domain-specific computing systems. We argue for the application of the same methodology to deep learning; specifically, we propose to extend neural…

Neural Architecture Search (NAS) has emerged as a key tool in identifying optimal configurations of deep neural networks tailored to specific tasks. However, training and assessing numerous architectures introduces considerable…

Energy efficiency and memory footprint of a convolutional neural network (CNN) implemented on a CNN inference accelerator depend on many factors, including a weight quantization strategy (i.e., data types and bit-widths) and mapping (i.e.,…

Many hardware vendors have introduced specialized deep neural networks (DNN) accelerators owing to their superior performance and efficiency. As such, how to generate and optimize the code for the hardware accelerator becomes an important…

Hardware-aware Neural Architecture Search (NAS) technologies have been proposed to automate and speed up model design to meet both quality and inference efficiency requirements on a given hardware. Prior arts have shown the capability of…

While Deep Neural Networks (DNNs) push the state-of-the-art in many machine learning applications, they often require millions of expensive floating-point operations for each input classification. This computation overhead limits the…

Speech Emotion Recognition (SER) is a critical enabler of emotion-aware communication in human-computer interactions. Recent advancements in Deep Learning (DL) have substantially enhanced the performance of SER models through increased…

Recent studies identify that Deep learning Neural Networks (DNNs) are vulnerable to subtle perturbations, which are not perceptible to human visual system but can fool the DNN models and lead to wrong outputs. A class of adversarial attack…

Differentiable Architecture Search (DARTS) has attracted extensive attention due to its efficiency in searching for cell structures. DARTS mainly focuses on the operation search and derives the cell topology from the operation weights.…

Neural architecture search (NAS) methods rely on a search strategy for deciding which architectures to evaluate next and a performance estimation strategy for assessing their performance (e.g., using full evaluations, multi-fidelity…