English
Related papers

Related papers: Exploring loss function topology with cyclical lea…

200 papers

The cross-entropy softmax loss is the primary loss function used to train deep neural networks. On the other hand, the focal loss function has been demonstrated to provide improved performance when there is an imbalance in the number of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-17 Leslie N. Smith

Convolutional Neural Networks (CNNs) dominate various computer vision tasks since Alex Krizhevsky showed that they can be trained effectively and reduced the top-5 error from 26.2 % to 15.3 % on the ImageNet large scale visual recognition…

Computer Vision and Pattern Recognition · Computer Science 2017-08-01 Martin Thoma

In-context learning (ICL) is a key building block of modern large language models, yet its theoretical mechanisms remain poorly understood. It is particularly mysterious how ICL operates in real-world applications where tasks have a common…

Disordered Systems and Neural Networks · Physics 2026-04-24 Kaito Takanami , Takashi Takahashi , Yoshiyuki Kabashima

The rapid growth in mobile broadband usage and increasing subscribers have made it crucial to ensure reliable network performance. As mobile networks grow more complex, especially during peak hours, manual collection of Key Performance…

Networking and Internet Architecture · Computer Science 2024-10-08 Nooruddin Noonari , Daniel Corujo , Rui L. Aguiar , Francisco J. Ferrao

Controllability has become a crucial aspect of trustworthy machine learning, enabling learners to meet predefined targets and adapt dynamically at test time without requiring retraining as the targets shift. We provide a formal definition…

Machine Learning · Computer Science 2025-08-07 Chenglei Shen , Xiao Zhang , Teng Shi , Changshuo Zhang , Guofu Xie , Jun Xu

Contemporary neural networks are limited in their ability to learn from evolving streams of training data. When trained sequentially on new or evolving tasks, their accuracy drops sharply, making them unsuitable for many real-world…

Computer Vision and Pattern Recognition · Computer Science 2021-02-19 Sudhanshu Mittal , Silvio Galesso , Thomas Brox

Following the traditional paradigm of convolutional neural networks (CNNs), modern CNNs manage to keep pace with more recent, for example transformer-based, models by not only increasing model depth and width but also the kernel size. This…

Computer Vision and Pattern Recognition · Computer Science 2023-06-23 Paul Gavrikov , Janis Keuper

Learning useful data representations without requiring labels is a cornerstone of modern deep learning. Self-supervised learning methods, particularly contrastive learning (CL), have proven successful by leveraging data augmentations to…

Machine Learning · Computer Science 2023-12-11 Sacha Morin , Somjit Nath , Samira Ebrahimi Kahou , Guy Wolf

Deep neural networks have shown remarkable performance when trained on independent and identically distributed data from a fixed set of classes. However, in real-world scenarios, it can be desirable to train models on a continuous stream of…

Machine Learning · Computer Science 2023-09-04 Nicolas Michel , Giovanni Chierchia , Romain Negrel , Jean-François Bercher , Toshihiko Yamasaki

In class-incremental learning, the objective is to learn a number of classes sequentially without having access to the whole training data. However, due to a problem known as catastrophic forgetting, neural networks suffer substantial…

Machine Learning · Computer Science 2021-06-01 Sobirdzhon Bobiev , Adil Khan , Syed Muhammad Ahsan Raza Kazmi

A convolutional layer in a Convolutional Neural Network (CNN) consists of many filters which apply convolution operation to the input, capture some special patterns and pass the result to the next layer. If the same patterns also occur at…

Computer Vision and Pattern Recognition · Computer Science 2019-02-04 Okan Köpüklü , Maryam Babaee , Stefan Hörmann , Gerhard Rigoll

Approaches to continual learning aim to successfully learn a set of related tasks that arrive in an online manner. Recently, several frameworks have been developed which enable deep learning to be deployed in this learning scenario. A key…

Machine Learning · Statistics 2020-06-17 Tameem Adel , Han Zhao , Richard E. Turner

Transfer learning (TL) is becoming a powerful tool in scientific applications of neural networks (NNs), such as weather/climate prediction and turbulence modeling. TL enables out-of-distribution generalization (e.g., extrapolation in…

Fluid Dynamics · Physics 2023-07-04 Adam Subel , Yifei Guan , Ashesh Chattopadhyay , Pedram Hassanzadeh

The field of meta-learning has seen a dramatic rise in interest in recent years. In existing meta-learning approaches, learning tasks for training meta-models are usually collected from public datasets, which brings the difficulty of…

Machine Learning · Computer Science 2021-11-23 Zhaoyang Hai , Xiabi Liu , Yuchen Ren , Nouman Q. Soomro

Existing work on continual learning (CL) is primarily devoted to developing algorithms for models trained from scratch. Despite their encouraging performance on contrived benchmarks, these algorithms show dramatic performance drops in…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Kuan-Ying Lee , Yuanyi Zhong , Yu-Xiong Wang

Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Lu Yu , Bartłomiej Twardowski , Xialei Liu , Luis Herranz , Kai Wang , Yongmei Cheng , Shangling Jui , Joost van de Weijer

Off-the-shelf machine learning algorithms for prediction such as regularized logistic regression cannot exploit the information of time-varying features without previously using an aggregation procedure of such sequential data. However,…

Applications · Statistics 2019-09-26 C. Gary Mena , Arno De Caigny , Kristof Coussement , Koen W. De Bock , Stefan Lessmann

This paper studies the challenging continual learning (CL) setting of Class Incremental Learning (CIL). CIL learns a sequence of tasks consisting of disjoint sets of concepts or classes. At any time, a single model is built that can be…

Machine Learning · Computer Science 2023-06-23 Gyuhak Kim , Changnan Xiao , Tatsuya Konishi , Bing Liu

This paper addresses the problem of visual feature representation learning with an aim to improve the performance of end-to-end reinforcement learning (RL) models. Specifically, a novel architecture is proposed that uses a heterogeneous…

Computer Vision and Pattern Recognition · Computer Science 2023-03-02 Darshita Jain , Anima Majumder , Samrat Dutta , Swagat Kumar

We present an empirical study on the use of continual learning (CL) methods in a reinforcement learning (RL) scenario, which, to the best of our knowledge, has not been described before. CL is a very active recent research topic concerned…

Machine Learning · Computer Science 2024-09-04 Benedikt Bagus , Alexander Gepperth