Fermeture de la BCU-Centrale suite au déménagement: 4 juillet – 16 août : La BCU-Centrale est fermée pour déménagement. Les commandes en magasins ainsi que les demandes de prêt entre bibliothèques ne seront pas possibles.
17 août : Réouverture de la BCU à Beauregard (rue de la Carrière 22)
Hors campus: Membres de la communauté universitaire ou de la HES-SO: n'oubliez pas d'utiliser le VPN de votre institution pour bénéficier de tous les accès.
Titre: Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation Auteur:Chung, Yu-An; Lin, Hsuan-Tien Sujet:Computer Science - Computer Vision And Pattern Recognition Description:
While deep neural networks have succeeded in several visual applications, such as object recognition, detection, and localization, by reaching very high classification accuracies, it is important to note that many real-world applications demand vary- ing costs for different types of misclassification errors, thus requiring cost-sensitive classification algorithms. Current models of deep neural networks for cost-sensitive classification are restricted to some specific network structures and limited depth. In this paper, we propose a novel framework that can be applied to deep neural networks with any structure to facilitate their learning of meaningful representations for cost-sensitive classification problems. Furthermore, the framework allows end- to-end training of deeper networks directly. The framework is designed by augmenting auxiliary neurons to the output of each hidden layer for layer-wise cost estimation, and including the total estimation loss within the optimization objective. Experimental results on public benchmark visual data sets with two cost information settings demonstrate that the proposed frame- work outperforms state-of-the-art cost-sensitive deep learning models.
1611.05134 (ARXIV ID)
Titre: Active Sampling of Pairs and Points for Large-scale Linear Bipartite Ranking Auteur:Shen, Wei-Yuan; Lin, Hsuan-Tien Sujet:Computer Science - Learning ; Computer Science - Information Retrieval Description:
Bipartite ranking is a fundamental ranking problem that learns to order relevant instances ahead of irrelevant ones. The pair-wise approach for bi-partite ranking construct a quadratic number of pairs to solve the problem, which is infeasible for large-scale data sets. The point-wise approach, albeit more efficient, often results in inferior performance. That is, it is difficult to conduct bipartite ranking accurately and efficiently at the same time. In this paper, we develop a novel active sampling scheme within the pair-wise approach to conduct bipartite ranking efficiently. The scheme is inspired from active learning and can reach a competitive ranking performance while focusing only on a small subset of the many pairs during training. Moreover, we propose a general Combined Ranking and Classification (CRC) framework to accurately conduct bipartite ranking. The framework unifies point-wise and pair-wise approaches and is simply based on the idea of treating each instance point as a pseudo-pair. Experiments on 14 real-word large-scale data sets demonstrate that the proposed algorithm of Active Sampling within CRC, when coupled with a linear Support Vector Machine, usually outperforms state-of-the-art point-wise and pair-wise ranking approaches in terms of both accuracy and efficiency. Comment: a shorter version was presented in ACML 2013
1708.07336 (ARXIV ID)
Cost-sensitive label embedding for multi-label classification
Huang, Kuan-Hao, Lin, Hsuan-Tien
Machine Learning, 2017, Vol.106(9), pp.1725-1746
[Revue évaluée par les pairs]
Titre: Automatic Bridge Bidding Using Deep Reinforcement Learning Auteur:Yeh, Chih-Kuan; Lin, Hsuan-Tien Sujet:Computer Science - Artificial Intelligence Description:
Bridge is among the zero-sum games for which artificial intelligence has not yet outperformed expert human players. The main difficulty lies in the bidding phase of bridge, which requires cooperative decision making under partial information. Existing artificial intelligence systems for bridge bidding rely on and are thus restricted by human-designed bidding systems or features. In this work, we propose a pioneering bridge bidding system without the aid of human domain knowledge. The system is based on a novel deep reinforcement learning model, which extracts sophisticated features and learns to bid automatically based on raw card data. The model includes an upper-confidence-bound algorithm and additional techniques to achieve a balance between exploration and exploitation. Our experiments validate the promising performance of our proposed model. In particular, the model advances from having no knowledge about bidding to achieving superior performance when compared with a champion-winning computer bridge program that implements a human-designed bidding system. Comment: 8 pages, 1 figure, 2016 ECAI accepted
1607.03290 (ARXIV ID)
Titre: Can Active Learning Experience Be Transferred? Auteur:Chu, Hong-Min; Lin, Hsuan-Tien Sujet:Computer Science - Learning ; Computer Science - Artificial Intelligence Description:
Active learning is an important machine learning problem in reducing the human labeling effort. Current active learning strategies are designed from human knowledge, and are applied on each dataset in an immutable manner. In other words, experience about the usefulness of strategies cannot be updated and transferred to improve active learning on other datasets. This paper initiates a pioneering study on whether active learning experience can be transferred. We first propose a novel active learning model that linearly aggregates existing strategies. The linear weights can then be used to represent the active learning experience. We equip the model with the popular linear upper- confidence-bound (LinUCB) algorithm for contextual bandit to update the weights. Finally, we extend our model to transfer the experience across datasets with the technique of biased regularization. Empirical studies demonstrate that the learned experience not only is competitive with existing strategies on most single datasets, but also can be transferred across datasets to improve the performance on future learning tasks. Comment: 10 pages, 8 figs, 4 tables, conference
1608.00667 (ARXIV ID)
Active Learning Using Hint Information.
Li, Chun-Liang, Ferng, Chun-Sung, Lin, Hsuan-Tien
Neural computation, August 2015, Vol.27(8), pp.1738-1765
[Revue évaluée par les pairs]