相关论文: SpaceEvo: Hardware-Friendly Search Space Design fo…

Approximate Nearest Neighbor Search (ANNS) in high-dimensional Euclidean spaces is a fundamental problem with broad applications. Subspace Collision is a newly proposed ANNS framework that provides a novel paradigm for similarity search and…

Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of…

Customized hardware accelerators have been developed to provide improved performance and efficiency for DNN inference and training. However, the existing hardware accelerators may not always be suitable for handling various DNN models as…

In the past few years, channel-wise and spatial-wise attention blocks have been widely adopted as supplementary modules in deep neural networks, enhancing network representational abilities while introducing low complexity. Most attention…

Although the quest for more accurate solutions is pushing deep learning research towards larger and more complex algorithms, edge devices demand efficient inference and therefore reduction in model size, latency and energy consumption. One…

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…

We develop a new computational framework to solve sequential Bayesian optimal experimental design (SBOED) problems constrained by large-scale partial differential equations with infinite-dimensional random parameters. We propose an adaptive…

With the popularity of deep learning, the hardware implementation platform of deep learning has received increasing interest. Unlike the general purpose devices, e.g., CPU, or GPU, where the deep learning algorithms are executed at the…

In the past decade, many architectures of convolution neural networks were designed by handcraft, such as Vgg16, ResNet, DenseNet, etc. They all achieve state-of-the-art level on different tasks in their time. However, it still relies on…

Recently, much attention has been spent on neural architecture search (NAS), aiming to outperform those manually-designed neural architectures on high-level vision recognition tasks. Inspired by the success, here we attempt to leverage NAS…

Designing accurate and efficient ConvNets for mobile devices is challenging because the design space is combinatorially large. Due to this, previous neural architecture search (NAS) methods are computationally expensive. ConvNet…

As the foundation of large language models (LLMs), self-attention module faces the challenge of quadratic time and memory complexity with respect to sequence length. FlashAttention accelerates attention computation and reduces its memory…

The last few years have seen gigantic leaps in algorithms and systems to support efficient deep learning inference. Pruning and quantization algorithms can now consistently compress neural networks by an order of magnitude. For a compressed…

Deploying quantized deep neural network (DNN) models with resource adaptation capabilities on ubiquitous Internet of Things (IoT) devices to provide high-quality AI services can leverage the benefits of compression and meet multi-scenario…

Deformable Attention Transformers (DAT) have shown remarkable performance in computer vision tasks by adaptively focusing on informative image regions. However, their data-dependent sampling mechanism introduces irregular memory access…

This paper introduces neural architecture search (NAS) for the automatic discovery of end-to-end keyword spotting (KWS) models in limited resource environments. We employ a differentiable NAS approach to optimize the structure of…

Reducing computational costs is an important issue for development of embedded systems. Binary-weight Neural Networks (BNNs), in which weights are binarized and activations are quantized, are employed to reduce computational costs of…

The ongoing advancements in network architecture design have led to remarkable achievements in deep learning across various challenging computer vision tasks. Meanwhile, the development of neural architecture search (NAS) has provided…

Reliable yet efficient evaluation of generalisation performance of a proposed architecture is crucial to the success of neural architecture search (NAS). Traditional approaches face a variety of limitations: training each architecture to…

Improving search efficiency serves as one of the crucial objectives of Neural Architecture Search (NAS). However, many current approaches ignore the universality of the search strategy and fail to reduce the computational redundancy during…