相关论文: Rethinking the Potential of Layer Freezing for Eff…

Recently, sparse training has emerged as a promising paradigm for efficient deep learning on edge devices. The current research mainly devotes efforts to reducing training costs by further increasing model sparsity. However, increasing…

In recent years, great progress has been made in a variety of application domains thanks to the development of increasingly deeper neural networks. Unfortunately, the huge number of units of these networks makes them expensive both…

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 (DNNs) are becoming increasingly deeper, wider, and non-linear due to the growing demands on prediction accuracy and analysis quality. When training a DNN model, the intermediate activation data must be saved in the…

Deep Neural Networks (DNNs) have become an essential component in many application domains including web-based services. A variety of these services require high throughput and (close to) real-time features, for instance, to respond or…

There has been a proliferation of artificial intelligence applications, where model training is key to promising high-quality services for these applications. However, the model training process is both time-intensive and energy-intensive,…

Recent advances in deep learning have made available large, powerful convolutional neural networks (CNN) with state-of-the-art performance in several real-world applications. Unfortunately, these large-sized models have millions of…

The emerging Learned Compression (LC) replaces the traditional codec modules with Deep Neural Networks (DNN), which are trained end-to-end for rate-distortion performance. This approach is considered as the future of image/video…

Deep Neural Network (DNN) has gained unprecedented performance due to its automated feature extraction capability. This high order performance leads to significant incorporation of DNN models in different Internet of Things (IoT)…

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

An increasing number of artificial intelligence (AI) applications involve the execution of deep neural networks (DNNs) on edge devices. Many practical reasons motivate the need to update the DNN model on the edge device post-deployment,…

Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel…

Training wide and deep neural networks (DNNs) require large amounts of storage resources such as memory because the intermediate activation data must be saved in the memory during forward propagation and then restored for backward…

Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising direction for reducing training cost is dataset…

Deep neural networks (DNNs) have recently achieved great success in many visual recognition tasks. However, existing deep neural network models are computationally expensive and memory intensive, hindering their deployment in devices with…

Thanks to their state-of-the-art performance, deep neural networks are increasingly used for object recognition. To achieve these results, they use millions of parameters to be trained. However, when targeting embedded applications the size…

Deep neural networks (DNNs) have been widely used in many artificial intelligence (AI) tasks. However, deploying them brings significant challenges due to the huge cost of memory, energy, and computation. To address these challenges,…

Low-Rank Factorization (LRF) is a widely adopted technique for compressing deep neural networks (DNNs). However, it faces several challenges, including optimal rank selection, a vast design space, long fine-tuning times, and limited…

As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive. This paper proposes a training set synthesis technique for…

Deep Convolutional Neural Networks (CNN) have been successfully applied to many real-life problems. However, the huge memory cost of deep CNN models poses a great challenge of deploying them on memory-constrained devices (e.g., mobile…