Zobrazeno 1 - 10
of 146
pro vyhledávání: '"Grandvalet, yves"'
In many large-scale classification problems, classes are organized in a known hierarchy, typically represented as a tree expressing the inclusion of classes in superclasses. We introduce a loss for this type of supervised hierarchical classification.
Externí odkaz:
http://arxiv.org/abs/2411.16438
Publikováno v:
International Joint Conference on Mechanics, Design Engineering & Advanced Manufacturing (JCM 2022), Jun 2022, Ischia, Italy. pp.1527--1538
The field of industrial defect detection using machine learning and deep learning is a subject of active research. Datasets, also called benchmarks, are used to compare and assess research results. There is a number of datasets in industrial visual i
Externí odkaz:
http://arxiv.org/abs/2305.13261
Publikováno v:
In Computers in Industry December 2024 163
Missing data can be informative. Ignoring this information can lead to misleading conclusions when the data model does not allow information to be extracted from the missing data. We propose a co-clustering model, based on the Latent Block Model, tha
Externí odkaz:
http://arxiv.org/abs/2010.12222
Camera-based end-to-end driving neural networks bring the promise of a low-cost system that maps camera images to driving control commands. These networks are appealing because they replace laborious hand engineered building blocks but their black-bo
Externí odkaz:
http://arxiv.org/abs/2008.04047
Learning generic representations with deep networks requires massive training samples and significant computer resources. To learn a new specific task, an important issue is to transfer the generic teacher's representation to a student network. In th
Externí odkaz:
http://arxiv.org/abs/2007.06737
In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which are at le
Externí odkaz:
http://arxiv.org/abs/1802.01483
This paper tackles the problem of endogenous link prediction for Knowledge Base completion. Knowledge Bases can be represented as directed graphs whose nodes correspond to entities and edges to relationships. Previous attempts either consist of power
Externí odkaz:
http://arxiv.org/abs/1506.00999
Numerous variable selection methods rely on a two-stage procedure, where a sparsity-inducing penalty is used in the first stage to predict the support, which is then conveyed to the second stage for estimation or inference purposes. In this framework
Externí odkaz:
http://arxiv.org/abs/1505.07281
Non-linear performance measures are widely used for the evaluation of learning algorithms. For example, $F$-measure is a commonly used performance measure for classification problems in machine learning and information retrieval community. We study t
Externí odkaz:
http://arxiv.org/abs/1505.00199