相关论文: SPRING: A Sparsity-Aware Reduced-Precision Monolit…

Due to complex interactions among various deep neural network (DNN) optimization techniques, modern DNNs can have weights and activations that are dense or sparse with diverse sparsity degrees. To offer a good trade-off between accuracy and…

Exploiting sparsity underlying neural networks has become one of the most potential methodologies to reduce the memory footprint, I/O cost, and computation workloads during inference. And the degree of sparsity one can exploit has become…

Distributed training is the de facto standard to scale up the training of deep learning models with multiple GPUs. Its performance bottleneck lies in communications for gradient synchronization. Although high tensor sparsity is widely…

Mobile devices are becoming an important carrier for deep learning tasks, as they are being equipped with powerful, high-end mobile CPUs and GPUs. However, it is still a challenging task to execute 3D Convolutional Neural Networks (CNNs)…

Spiking transformers are emerging as a promising architecture that combines the energy efficiency of Spiking Neural Networks (SNNs) with the powerful attention mechanisms of transformers. However, existing hardware accelerators lack support…

Sparseness is a useful regularizer for learning in a wide range of applications, in particular in neural networks. This paper proposes a model targeted at classification tasks, where sparse activity and sparse connectivity are used to…

Convolutional Neural Networks are extensively used in a wide range of applications, commonly including computer vision tasks like image and video classification, recognition, and segmentation. Recent research results demonstrate that…

Although state-of-the-art (SOTA) CNNs achieve outstanding performance on various tasks, their high computation demand and massive number of parameters make it difficult to deploy these SOTA CNNs onto resource-constrained devices. Previous…

Modern efficient Convolutional Neural Networks(CNNs) always use Depthwise Separable Convolutions(DSCs) and Neural Architecture Search(NAS) to reduce the number of parameters and the computational complexity. But some inherent…

In-network computing techniques, exemplified by NVLink SHARP (NVLS), offer a promising approach to addressing the communication bottlenecks in LLM inference by offloading collective operations such as All-Reduce to switches. However, the…

Convolutional neural networks (CNNs) are revolutionizing machine learning, but they present significant computational challenges. Recently, many FPGA-based accelerators have been proposed to improve the performance and efficiency of CNNs.…

Spiking Neural Networks (SNNs) are being explored for their potential energy efficiency resulting from sparse, event-driven computations. Many recent works have demonstrated effective backpropagation for deep Spiking Neural Networks (SNNs)…

Nowadays, increasingly larger Deep Neural Networks (DNNs) are being developed, trained, and utilized. These networks require significant computational resources, putting a strain on both advanced and limited devices. Our solution is to…

The human brain utilizes spikes for information transmission and dynamically reorganizes its network structure to boost energy efficiency and cognitive capabilities throughout its lifespan. Drawing inspiration from this spike-based…

Deep neural networks have achieved remarkable accuracy in many artificial intelligence applications, e.g. computer vision, at the cost of a large number of parameters and high computational complexity. Weight pruning can compress DNN models…

The simultaneous restoration of high-frequency details and suppression of severe noise in low-light imagery presents a significant and persistent challenge in computer vision. While large-scale Transformer models like SwinIR have set the…

We propose a generalized convolutional neural network (CNN) architecture that first decomposes the input signal into subbands by an adaptive filter bank structure, and then uses convolutional layers to extract features from each subband…

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

Non-uniformed 3D sparse data, e.g., point clouds or voxels in different spatial positions, make contribution to the task of 3D object detection in different ways. Existing basic components in sparse convolutional networks (Sparse CNNs)…

Convolutional Neural Networks (CNNs) serve various applications with diverse performance and resource requirements. Model-aware CNN accelerators best address these diverse requirements. These accelerators usually combine multiple dedicated…