Related papers: GhostNetV3: Exploring the Training Strategies for …

Long training times for high-accuracy deep neural networks (DNNs) impede research into new DNN architectures and slow the development of high-accuracy DNNs. In this paper we present FireCaffe, which successfully scales deep neural network…

Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in…

Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of…

Graph Neural Networks (GNNs) have shown great superiority on non-Euclidean graph data, achieving ground-breaking performance on various graph-related tasks. As a practical solution to train GNN on large graphs with billions of nodes and…

Humans can easily detect a defect (anomaly) because it is different or salient when compared to the surface it resides on. Today, manual human visual inspection is still the norm because it is difficult to automate anomaly detection. Neural…

Designing neural networks typically relies on manual trial and error or a neural architecture search (NAS) followed by weight training. The former is time-consuming and labor-intensive, while the latter often discretizes architecture search…

As the volume of image data grows, data-oriented cloud computing in Internet of Video Things (IoVT) systems encounters latency issues. Task-oriented edge computing addresses this by shifting data analysis to the edge. However, limited…

We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), this paper focuses on…

Machine learning classifiers using surface electromyography are important for human-machine interfacing and device control. Conventional classifiers such as support vector machines (SVMs) use manually extracted features based on e.g.…

Neural operators (NOs) employ deep neural networks to learn mappings between infinite-dimensional function spaces. Deep operator network (DeepONet), a popular NO architecture, has demonstrated success in the real-time prediction of complex…

As neural networks grow deeper and wider, learning networks with hard-threshold activations is becoming increasingly important, both for network quantization, which can drastically reduce time and energy requirements, and for creating large…

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

Modern object detectors can rarely achieve short training time, fast inference speed, and high accuracy at the same time. To strike a balance among them, we propose the Training-Time-Friendly Network (TTFNet). In this work, we start with…

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…

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow…

The training of deep and/or convolutional neural networks (DNNs/CNNs) is traditionally done on servers with powerful CPUs and GPUs. Recent efforts have emerged to localize machine learning tasks fully on the edge. This brings advantages in…

Recently, a new trend of exploring sparsity for accelerating neural network training has emerged, embracing the paradigm of training on the edge. This paper proposes a novel Memory-Economic Sparse Training (MEST) framework targeting for…

Real-time understanding in video is crucial in various AI applications such as autonomous driving. This work presents a fast single-shot segmentation strategy for video scene understanding. The proposed net, called S3-Net, quickly locates…

Deep video recognition is more computationally expensive than image recognition, especially on large-scale datasets like Kinetics [1]. Therefore, training scalability is essential to handle a large amount of videos. In this paper, we study…

Pre-trained models have achieved state-of-the-art results in various Natural Language Processing (NLP) tasks. Recent works such as T5 and GPT-3 have shown that scaling up pre-trained language models can improve their generalization…