English
Related papers

Related papers: Enlightenment Period Improving DNN Performance

200 papers

Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient descent algorithms and achieve unexpected levels of…

Images cannot always be expected to come in a certain standard format and orientation. Deep networks need to be trained to take into account unexpected variations in orientation or format. For this purpose, training data should be enriched…

Computer Vision and Pattern Recognition · Computer Science 2023-06-14 Hakan Temiz

There is growing interest in the challenging visual perception task of learning from long-tailed class distributions. The extreme class imbalance in the training dataset biases the model to prefer recognizing majority class data over…

Computer Vision and Pattern Recognition · Computer Science 2024-02-19 Jae Soon Baik , In Young Yoon , Jun Won Choi

The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-the-art label-noise learning methods. To exploit this property, the early stopping trick, which stops the optimization at the early stage of…

Machine Learning · Computer Science 2021-12-28 Yingbin Bai , Erkun Yang , Bo Han , Yanhua Yang , Jiatong Li , Yinian Mao , Gang Niu , Tongliang Liu

We investigate the learning dynamics of fully-connected neural networks through the lens of gradient signal-to-noise ratio (SNR), examining the behavior of first-order optimizers like Adam in non-convex objectives. By interpreting the…

Machine Learning · Computer Science 2024-03-28 Sokratis J. Anagnostopoulos , Juan Diego Toscano , Nikolaos Stergiopulos , George Em Karniadakis

On-line Precision scalability of the deep neural networks(DNNs) is a critical feature to support accuracy and complexity trade-off during the DNN inference. In this paper, we propose dual-precision DNN that includes two different precision…

Machine Learning · Computer Science 2024-05-14 Jae Hyun Park , Ji Sub Choi , Jong Hwan Ko

Large-batch SGD is important for scaling training of deep neural networks. However, without fine-tuning hyperparameter schedules, the generalization of the model may be hampered. We propose to use batch augmentation: replicating instances…

Machine Learning · Computer Science 2019-01-29 Elad Hoffer , Tal Ben-Nun , Itay Hubara , Niv Giladi , Torsten Hoefler , Daniel Soudry

MixUp is an effective data augmentation method to regularize deep neural networks via random linear interpolations between pairs of samples and their labels. It plays an important role in model regularization, semi-supervised learning and…

Computer Vision and Pattern Recognition · Computer Science 2019-08-28 Zhijun Mai , Guosheng Hu , Dexiong Chen , Fumin Shen , Heng Tao Shen

Training neural networks is an optimization problem, and finding a decent set of parameters through gradient descent can be a difficult task. A host of techniques has been developed to aid this process before and during the training phase.…

Machine Learning · Computer Science 2020-08-19 Divya Gaur , Joachim Folz , Andreas Dengel

In this paper, we advocate for two stages in a neural network's decision making process. The first is the existing feed-forward inference framework where patterns in given data are sensed and associated with previously learned patterns. The…

Machine Learning · Computer Science 2022-09-20 Mohit Prabhushankar , Ghassan AlRegib

We show that the ability of a neural network to integrate information from diverse sources hinges critically on being exposed to properly correlated signals during the early phases of training. Interfering with the learning process during…

Machine Learning · Computer Science 2023-09-18 Michael Kleinman , Alessandro Achille , Stefano Soatto

Data augmentation is now an essential part of the image training process, as it effectively prevents overfitting and makes the model more robust against noisy datasets. Recent mixing augmentation strategies have advanced to generate the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-30 Minsoo Kang , Suhyun Kim

Standard deep neural networks (DNNs) are commonly trained in an end-to-end fashion for specific tasks such as object recognition, face identification, or character recognition, among many examples. This specificity often leads to…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Raphaël Achddou , J. Matias di Martino , Guillermo Sapiro

Deep neural networks (DNNs) are typically optimized using various forms of mini-batch gradient descent algorithm. A major motivation for mini-batch gradient descent is that with a suitably chosen batch size, available computing resources…

Machine Learning · Computer Science 2022-10-25 Oyebade K. Oyedotun , Konstantinos Papadopoulos , Djamila Aouada

Data augmentation has been actively studied for robust neural networks. Most of the recent data augmentation methods focus on augmenting datasets during the training phase. At the testing phase, simple transformations are still widely used…

Computer Vision and Pattern Recognition · Computer Science 2020-10-23 Ildoo Kim , Younghoon Kim , Sungwoong Kim

Deployment of real-time ML services on warehouse-scale infrastructures is on the increase. Therefore, decreasing latency and increasing throughput of deep neural network (DNN) inference applications that empower those services have…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-08-29 Seyed Morteza Nabavinejad , Masoumeh Ebrahimi , Sherief Reda

Mixup is a procedure for data augmentation that trains networks to make smoothly interpolated predictions between datapoints. Adversarial training is a strong form of data augmentation that optimizes for worst-case predictions in a compact…

Machine Learning · Computer Science 2021-03-23 Jason Bunk , Srinjoy Chattopadhyay , B. S. Manjunath , Shivkumar Chandrasekaran

Critical Learning Periods comprehend an important phenomenon involving deep learning, where early epochs play a decisive role in the success of many training recipes, such as data augmentation. Existing works confirm the existence of this…

Machine Learning · Computer Science 2025-11-11 Vinicius Yuiti Fukase , Heitor Gama , Barbara Bueno , Lucas Libanio , Anna Helena Reali Costa , Artur Jordao

Learning rate scheduling plays a critical role in the optimization of deep neural networks, directly influencing convergence speed, stability, and generalization. While existing schedulers such as cosine annealing, cyclical learning rates,…

Machine Learning · Computer Science 2026-03-05 Ayush K. Varshney , Šarūnas Girdzijauskas , Konstantinos Vandikas , Aneta Vulgarakis Feljan

We investigate the impact of entropy change in deep learning systems by noise injection at different levels, including the embedding space and the image. The series of models that employ our methodology are collectively known as Noisy…

Artificial Intelligence · Computer Science 2025-09-09 Xiaowei Yu , Zhe Huang , Minheng Chen , Lu Zhang , Tianming Liu , Dajiang Zhu
‹ Prev 1 4 5 6 7 8 10 Next ›