Results 31 to 40 of about 452,378 (262)

Transfer Incremental Learning Using Data Augmentation

Applied Sciences, 2018
Deep learning-based methods have reached state of the art performances, relying on a large quantity of available data and computational power. Such methods still remain highly inappropriate when facing a major open machine learning problem, which ...
Ghouthi Boukli Hacene, Vincent Gripon, Nicolas Farrugia, Matthieu Arzel, Michel Jezequel   +4 more
doaj   +1 more source

Enhancing Case-based Reasoning Approach using Incremental Learning Model for Automatic Adaptation of Classifiers in Mobile Phishing Detection

International Journal of Networked and Distributed Computing (IJNDC), 2020
This article presents the threshold-based incremental learning model for a case-base updating approach that can support adaptive detection and incremental learning of Case-based Reasoning (CBR)-based automatic adaptable phishing detection.
San Kyaw Zaw, Sangsuree Vasupongayya
doaj   +1 more source

Incremental multi‐view correlated feature learning based on non‐negative matrix factorisation

IET Computer Vision, 2021
In real‐world applications, large amounts of data from multiple sources come in the form of streams. This makes multi‐view feature learning cost much time when new instances rise incrementally.
Liang Zhao, Tao Yang, Jie Zhang, Zhikui Chen   +3 more
doaj   +1 more source

Incremental multiclass open-set audio recognition

IJAIN (International Journal of Advances in Intelligent Informatics), 2022
Incremental learning aims to learn new classes if they emerge while maintaining the performance for previously known classes. It acquires useful information from incoming data to update the existing models.
Hitham Jleed, Martin Bouchard
doaj   +1 more source

(Un)supervised (Co)adaptation via Incremental Learning for Myoelectric Control: Motivation, Review, and Future Directions

IEEE Transactions on Neural Systems and Rehabilitation Engineering
This paper presents a narrative review of incremental learning methods for myoelectric control, outlining both the historical trajectory and potential of adaptive prosthetic systems.
Evan Campbell, Fabio Egle, Marius OsWald, Ulysse Cote-Allard, Patrick M. Pilarski, Nicolo Boccardo, Roberto Meattini, Ivan Vujaklija, Levi Hargrove, Michele Canepa, Ethan Eddy, Alessandro Del Vecchio, Claudio Castellini, Erik Scheme   +13 more
doaj   +1 more source

Efficiently Updating ECG-Based Biometric Authentication Based on Incremental Learning

Sensors, 2021
Recently, the interest in biometric authentication based on electrocardiograms (ECGs) has increased. Nevertheless, the ECG signal of a person may vary according to factors such as the emotional or physical state, thus hindering authentication. We propose
Junmo Kim, Geunbo Yang, Juhyeong Kim, Seungmin Lee, Ko Keun Kim, Cheolsoo Park   +5 more
doaj   +1 more source

Population-based incremental learning with memory scheme for changing environments [PDF]

, 2005
Copyright @ 2005 ACMIn recent years there has been a growing interest in studying evolutionary algorithms for dynamic optimization problems due to its importance in real world applications.
Yang, S
core   +1 more source

Class Incremental Learning With Large Domain Shift

IEEE Access
We address an important and practical problem facing deep-learning-based image classification: class incremental learning with a large domain shift. Most previous efforts on class incremental learning focus on one aspect of the problem, i.e., learning to
Kamin Lee, Hyoeun Kim, Geunjae Choi, Hyejeong Jeon, Nojun Kwak   +4 more
doaj   +1 more source

Catastrophic forgetting: still a problem for DNNs

, 2019
We investigate the performance of DNNs when trained on class-incremental visual problems consisting of initial training, followed by retraining with added visual classes.
Abdullah, S., Gepperth, A., Kilian, A., Pfülb, B.   +3 more
core   +1 more source

Best-Choice Edge Grafting for Efficient Structure Learning of Markov Random Fields

, 2018
Incremental methods for structure learning of pairwise Markov random fields (MRFs), such as grafting, improve scalability by avoiding inference over the entire feature space in each optimization step. Instead, inference is performed over an incrementally
Chaabene, Walid, Huang, Bert
core   +1 more source