相关论文: Dense or Sparse? Post-Packing Interconnection Anal…

Delay Deviation Exceedance (DDE) and Differential Skew Exceedance (DSE) measures are proposed to quantify delay uncertainty in single-ended and differential PCB interconnects arising from Fiber Weave Effect (FWE). DDE and DSE are…

High-level synthesis (HLS) shortens the development time of hardware designs and enables faster design space exploration at a higher abstraction level. Optimization of complex applications in HLS is challenging due to the effects of…

Capsules as well as dynamic routing between them are most recently proposed structures for deep neural networks. A capsule groups data into vectors or matrices as poses rather than conventional scalars to represent specific properties of…

The deployment of deep neural networks (DNNs) on resource-constrained edge devices such as field-programmable gate arrays (FPGAs) requires a careful balance of latency, power, and resource usage while maintaining high accuracy. Existing…

Deep neural networks have made remarkable progresses on various computer vision tasks. Recent works have shown that depth, width and shortcut connections of networks are all vital to their performances. In this paper, we introduce a method…

Sparse matrices are the key ingredients of several application domains, from scientific computation to machine learning. The primary challenge with sparse matrices has been efficiently storing and transferring data, for which many sparse…

Compressive sensing (CS) exploits sparsity to recover sparse or compressible signals from dimensionality reducing, non-adaptive sensing mechanisms. Sparsity is also used to enhance interpretability in machine learning and statistics…

In recent years, there has been a flurry of research in deep neural network pruning and compression. Early approaches prune weights individually. However, it is difficult to take advantage of the resulting unstructured sparsity patterns on…

Prior works have shown that neural networks can be heavily pruned while preserving performance, but the impact of pruning on model interpretability remains unclear. In this work, we investigate how magnitude-based pruning followed by…

Transformers have made progress in miscellaneous tasks, but suffer from quadratic computational and memory complexities. Recent works propose sparse Transformers with attention on sparse graphs to reduce complexity and remain strong…

The demand for efficient processing of deep neural networks (DNNs) on embedded devices is a significant challenge limiting their deployment. Exploiting sparsity in the network's feature maps is one of the ways to reduce its inference…

This paper investigates the role of flexible connection in accelerating the interconnection of large loads amid rising electricity demand from data centers and electrification. Flexible connection allows new loads to defer or curtail…

Deploying large language models (LLMs) on end-user devices is gaining importance due to benefits in responsiveness, privacy, and operational cost. Yet the limited memory and compute capability of mobile and desktop GPUs make efficient…

The sparsity of Deep Neural Networks is well investigated to maximize the performance and reduce the size of overparameterized networks as possible. Existing methods focus on pruning parameters in the training process by using thresholds…

We perform an empirical study of the behaviour of deep networks when fully linearizing some of its feature channels through a sparsity prior on the overall number of nonlinear units in the network. In experiments on image classification and…

Efficient inference of Deep Neural Networks (DNNs) on resource-constrained edge devices is essential. Quantization and sparsity are key techniques that translate to repetition and sparsity within tensors at the hardware-software interface.…

Deep convolutional networks are well-known for their high computational and memory demands. Given limited resources, how does one design a network that balances its size, training time, and prediction accuracy? A surprisingly effective…

Network pruning can reduce the high computation cost of deep neural network (DNN) models. However, to maintain their accuracies, sparse models often carry randomly-distributed weights, leading to irregular computations. Consequently, sparse…

Networks are a unifying framework for modeling complex systems and network inference problems are frequently encountered in many fields. Here, I develop and apply a generative approach to network inference (RCweb) for the case when the…

Reconstruction of fine-scale information from sparse data is relevant to many practical fluid dynamic applications where the sensing is typically sparse. Fluid flows in an ideal sense are manifestations of nonlinear multiscale PDE dynamical…