Results 1  10
of
13
InformationMaximization Clustering based on SquaredLoss Mutual Information
"... Informationmaximization clustering learns a probabilistic classifier in an unsupervised manner so that mutual information between feature vectors and cluster assignments is maximized. A notable advantage of this approach is that it only involves continuous optimization of model parameters, which is ..."
Abstract

Cited by 7 (5 self)
 Add to MetaCart
(Show Context)
Informationmaximization clustering learns a probabilistic classifier in an unsupervised manner so that mutual information between feature vectors and cluster assignments is maximized. A notable advantage of this approach is that it only involves continuous optimization of model parameters, which is substantially simpler than discrete optimization of cluster assignments. However, existing methods still involve nonconvex optimization problems, and therefore finding a good local optimal solution is not straightforward in practice. In this paper, we propose an alternative informationmaximization clustering method based on a squaredloss variant of mutual information. This novel approach gives a clustering solution analytically in a computationally efficient way via kernel eigenvalue decomposition. Furthermore, we provide a practical model selection procedure that allows us to objectively optimize tuning parameters included in the kernel function. Through experiments, we demonstrate the usefulness of the proposed approach.
Transfer Learning for Activity Recognition: A Survey
"... Many intelligent systems that focus on the needs of a human require information about the activities being performed by the human. At the core of this capability is activity recognition, which is a challenging and wellresearched problem. Activity recognition algorithms require substantial amounts o ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
(Show Context)
Many intelligent systems that focus on the needs of a human require information about the activities being performed by the human. At the core of this capability is activity recognition, which is a challenging and wellresearched problem. Activity recognition algorithms require substantial amounts of labeled training data yet need to perform well under very diverse circumstances. As a result, researchers have been designing methods to identify and utilize subtle connections between activity recognition datasets, or to perform transferbased activity recognition. In this paper we survey the literature to highlight recent advances in transfer learning for activity recognition. We characterize existing approaches to transferbased activity recognition by sensor modality, by differences between source and target environments, by data availability, and by type of information that is transferred. Finally, we present some grand challenges for the community to consider as this field is further developed. 1
Covariate Shift Adaptation, ClassBalance Change Adaptation, and Change Detection
"... In standard supervised learning algorithms training and test data are assumed to follow the same probability distribution. However, because of a sample selection bias or nonstationarity of the environment, this important assumption is often violated in practice, which causes a signicant estimatio ..."
Abstract
 Add to MetaCart
(Show Context)
In standard supervised learning algorithms training and test data are assumed to follow the same probability distribution. However, because of a sample selection bias or nonstationarity of the environment, this important assumption is often violated in practice, which causes a signicant estimation bias. In this article, we review semisupervised adaptation techniques for coping with such distribution changes. We focus on two scenarios of such distribution change: the covariate shift (input distributions change but the inputoutput dependency does not change) and the classbalance change in classication (classprior probabilities change but classwise input distributions remain unchanged). We also show methods of change detection in probability distributions.
1WIREs Computational Statistics, 2013. Learning under NonStationarity: Covariate Shift and ClassBalance Change
"... One of the fundamental assumptions behind many supervised machine learning algorithms is that training and test data follow the same probability distribution. However, this important assumption is often violated in practice, for example, because of an unavoidable sample selection bias or nonstati ..."
Abstract
 Add to MetaCart
(Show Context)
One of the fundamental assumptions behind many supervised machine learning algorithms is that training and test data follow the same probability distribution. However, this important assumption is often violated in practice, for example, because of an unavoidable sample selection bias or nonstationarity of the environment. Due to violation of the assumption, standard machine learning methods suffer a significant estimation bias. In this article, we consider two scenarios of such distribution change — the covariate shift where input distributions differ and classbalance change where classprior probabilities vary in classification — and review semisupervised adaptation techniques based on importance weighting.
To appear in WIREs Computational Statistics. 1 Learning under NonStationarity: Covariate Shift and ClassBalance Change
"... One of the fundamental assumptions behind many supervised machine learning algorithms is that training and test data follow the same probability distribution. However, this important assumption is often violated in practice, for example, because of an unavoidable sample selection bias or nonstation ..."
Abstract
 Add to MetaCart
(Show Context)
One of the fundamental assumptions behind many supervised machine learning algorithms is that training and test data follow the same probability distribution. However, this important assumption is often violated in practice, for example, because of an unavoidable sample selection bias or nonstationarity of the environment. Due to violation of the assumption, standard machine learning methods suffer a significant estimation bias. In this article, we consider two scenarios of such distribution change — the covariate shift where input distributions differ and classbalance change where classprior probabilities vary in classification — and review semisupervised adaptation techniques based on importance weighting.
1 Early Stopping Heuristics in PoolBased Incremental Active Learning for LeastSquares Probabilistic Classifier
"... The objective of poolbased incremental active learning is to choose a sample to label from a pool of unlabeled samples in an incremental manner so that the generalization error is minimized. In this scenario, the generalization error often hits a minimum in the middle of the incremental active lear ..."
Abstract
 Add to MetaCart
(Show Context)
The objective of poolbased incremental active learning is to choose a sample to label from a pool of unlabeled samples in an incremental manner so that the generalization error is minimized. In this scenario, the generalization error often hits a minimum in the middle of the incremental active learning procedure and then it starts to increase. In this paper, we address the problem of early labeling stopping in probabilistic classification for minimizing the generalization error and the labeling cost. Among several possible strategies, we propose to stop labeling when the empirical classposterior approximation error is maximized. Experiments on benchmark datasets demonstrate the usefulness of the proposed strategy. Keywords poolbased incremental active learning, early stopping, leastsquares probabilistic
Covariate Shift Adaptation, ClassBalance Change Adaptation, and Change Detection
"... In standard supervised learning algorithms training and test data are assumed to follow the same probability distribution. However, because of a sample selection bias or nonstationarity of the environment, this important assumption is often violated in practice, which causes a signicant estimatio ..."
Abstract
 Add to MetaCart
(Show Context)
In standard supervised learning algorithms training and test data are assumed to follow the same probability distribution. However, because of a sample selection bias or nonstationarity of the environment, this important assumption is often violated in practice, which causes a signicant estimation bias. In this article, we review semisupervised adaptation techniques for coping with such distribution changes. We focus on two scenarios of such distribution change: the covariate shift (input distributions change but the inputoutput dependency does not change) and the classbalance change in classication (classprior probabilities change but classwise input distributions remain unchanged). We also show methods of change detection in probability distributions.
Density Ratio Hidden Markov Models
"... Hidden Markov models and their variants are the predominant sequential classification method in such domains as speech recognition, bioinformatics and natural language processing. Being generative rather than discriminative models, however, their classification performance is a drawback. In this pap ..."
Abstract
 Add to MetaCart
(Show Context)
Hidden Markov models and their variants are the predominant sequential classification method in such domains as speech recognition, bioinformatics and natural language processing. Being generative rather than discriminative models, however, their classification performance is a drawback. In this paper we apply ideas from the field of density ratio estimation to bypass the difficult step of learning likelihood functions in HMMs. By reformulating inference and model fitting in terms of density ratios and applying a fast kernelbased estimation method, we show that it is possible to obtain a striking increase in discriminative performance while retaining the probabilistic qualities of the HMM. We demonstrate experimentally that this formulation makes more efficient use of training data than alternative approaches. 1