Results 31 to 40 of about 440,724 (260)

Using the online cross-entropy method to learn relational policies for playing different games [PDF]

, 2011
By defining a video-game environment as a collection of objects, relations, actions and rewards, the relational reinforcement learning algorithm presented in this paper generates and optimises a set of concise, human-readable relational rules for ...
Driessens, Kurt, Pfahringer, Bernhard, Sarjant, Samuel, Smith, Tony C.   +3 more
core   +4 more sources

Learning Entropy: Multiscale Measure for Incremental Learning

Entropy, 2013
First, this paper recalls a recently introduced method of adaptive monitoring of dynamical systems and presents the most recent extension with a multiscale-enhanced approach.
Ivo Bukovsky
doaj   +1 more source

Incremental Learning of Latent Forests

IEEE Access, 2020
In the analysis of real-world data, it is useful to learn a latent variable model that represents the data generation process. In this setting, latent tree models are useful because they are able to capture complex relationships while being easily ...
Fernando Rodriguez-Sanchez, Pedro Larranaga, Concha Bielza   +2 more
doaj   +1 more source

Chunk Incremental Canonical Correlation Analysis [PDF]

Jisuanji kexue yu tansuo, 2022
For the large-scale dynamic data stream, incremental learning is an effective and efficient technique and is widely used in machine learning. Incremental dimensionality reduction algorithms have been proposed by many scholars.
PAN Yu, CHEN Xiaohong, LI Shunming, LI Jiyong
doaj   +1 more source

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

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

New Generation Federated Learning

Sensors, 2022
With the development of the Internet of things (IoT), federated learning (FL) has received increasing attention as a distributed machine learning (ML) framework that does not require data exchange. However, current FL frameworks follow an idealized setup
Boyuan Li, Shengbo Chen, Zihao Peng
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

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