相关论文: Efficient Post-Training Augmentation for Adaptive …

Increasing resolution and coverage of astrophysical and climate data necessitates increasingly sophisticated models, often pushing the limits of computational feasibility. While emulation methods can reduce calculation costs, the neural…

Deep neural networks (DNN) have achieved remarkable success in computer vision (CV). However, training and inference of DNN models are both memory and computation intensive, incurring significant overhead in terms of energy consumption and…

Deep neural networks (DNNs) have achieved great success in the area of computer vision. The disparity estimation problem tends to be addressed by DNNs which achieve much better prediction accuracy than traditional hand-crafted feature-based…

Recurrent Neural Network (RNN) inference exhibits low hardware utilization due to the strict data dependencies across time-steps. Batching multiple requests can increase throughput. However, RNN batching requires a large amount of padding…

By leveraging the data sample diversity, the early-exit network recently emerges as a prominent neural network architecture to accelerate the deep learning inference process. However, intermediate classifiers of the early exits introduce…

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…

Deploying deep learning models in time-critical applications with limited computational resources, for instance in edge computing systems and IoT networks, is a challenging task that often relies on dynamic inference methods such as early…

Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others. However, continuously…

Many evolutionary algorithms (EAs) take advantage of parallel evaluation of candidates. However, if evaluation times vary significantly, many worker nodes (i.e.,\ compute clients) are idle much of the time, waiting for the next generation…

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…

Large Language Models (LLMs) based on transformers achieve cutting-edge results on a variety of applications. However, their enormous size and processing requirements hinder deployment on constrained resources. To enhance efficiency,…

Fully Connected Neural Networks (FCNNs) have been the core of most state-of-the-art Machine Learning (ML) applications in recent years and also have been widely used for Intrusion Detection Systems (IDSs). Experimental results from the last…

Over the last few years, Deep Neural Networks (DNNs) have become ubiquitous owing to their high accuracy on real-world tasks. However, this increase in accuracy comes at the cost of computationally expensive models leading to higher…

Deep neural networks (DNN) have shown superior performance in a variety of tasks. As they rapidly evolve, their escalating computation and memory demands make it challenging to deploy them on resource-constrained edge devices. Though…

By adding exiting layers to the deep learning networks, early exit can terminate the inference earlier with accurate results. The passive decision-making of whether to exit or continue the next layer has to go through every pre-placed…

This work aims to enable on-device training of convolutional neural networks (CNNs) by reducing the computation cost at training time. CNN models are usually trained on high-performance computers and only the trained models are deployed to…

Spiking Neural Networks (SNNs) exhibit exceptional energy efficiency on neuromorphic hardware due to their sparse activation patterns. However, conventional training methods based on surrogate gradients and Backpropagation Through Time…

Dilated and transposed convolutions are widely used in modern convolutional neural networks (CNNs). These kernels are used extensively during CNN training and inference of applications such as image segmentation and high-resolution image…

Early exiting is an effective paradigm for improving the inference efficiency of deep networks. By constructing classifiers with varying resource demands (the exits), such networks allow easy samples to be output at early exits, removing…

A critical factor in adopting machine learning for time-sensitive financial tasks is computational speed, including model training and inference. This paper demonstrates that a broad class of such problems, especially those previously…