Results 1  10
of
653
A Survey on Transfer Learning
"... A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many realworld applications, this assumption may not hold. For example, we sometimes have a classification task i ..."
Abstract

Cited by 443 (22 self)
 Add to MetaCart
A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many realworld applications, this assumption may not hold. For example, we sometimes have a classification task in one domain of interest, but we only have sufficient training data in another domain of interest, where the latter data may be in a different feature space or follow a different data distribution. In such cases, knowledge transfer, if done successfully, would greatly improve the performance of learning by avoiding much expensive data labeling efforts. In recent years, transfer learning has emerged as a new learning framework to address this problem. This survey focuses on categorizing and reviewing the current progress on transfer learning for classification, regression and clustering problems. In this survey, we discuss the relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift. We also explore some potential future issues in transfer learning research.
A framework for learning predictive structures from multiple tasks and unlabeled data
 Journal of Machine Learning Research
, 2005
"... One of the most important issues in machine learning is whether one can improve the performance of a supervised learning algorithm by including unlabeled data. Methods that use both labeled and unlabeled data are generally referred to as semisupervised learning. Although a number of such methods ar ..."
Abstract

Cited by 440 (3 self)
 Add to MetaCart
One of the most important issues in machine learning is whether one can improve the performance of a supervised learning algorithm by including unlabeled data. Methods that use both labeled and unlabeled data are generally referred to as semisupervised learning. Although a number of such methods are proposed, at the current stage, we still don’t have a complete understanding of their effectiveness. This paper investigates a closely related problem, which leads to a novel approach to semisupervised learning. Specifically we consider learning predictive structures on hypothesis spaces (that is, what kind of classifiers have good predictive power) from multiple learning tasks. We present a general framework in which the structural learning problem can be formulated and analyzed theoretically, and relate it to learning with unlabeled data. Under this framework, algorithms for structural learning will be proposed, and computational issues will be investigated. Experiments will be given to demonstrate the effectiveness of the proposed algorithms in the semisupervised learning setting. 1.
Describing objects by their attributes
 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR
, 2009
"... We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar object (“spotty dog”, not just “dog”); to say something about unfamiliar objects (“hairy and fourlegged”, not just “unknown” ..."
Abstract

Cited by 349 (17 self)
 Add to MetaCart
(Show Context)
We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar object (“spotty dog”, not just “dog”); to say something about unfamiliar objects (“hairy and fourlegged”, not just “unknown”); and to learn how to recognize new objects with few or no visual examples. Rather than focusing on identity assignment, we make inferring attributes the core problem of recognition. These attributes can be semantic (“spotty”) or discriminative (“dogs have it but sheep do not”). Learning attributes presents a major new challenge: generalization across object categories, not just across instances within a category. In this paper, we also introduce a novel feature selection method for learning attributes that generalize well across categories. We support our claims by thorough evaluation that provides insights into the limitations of the standard recognition paradigm of naming and demonstrates the new abilities provided by our attributebased framework. 1.
Bayesian Compressive Sensing
, 2007
"... The data of interest are assumed to be represented as Ndimensional real vectors, and these vectors are compressible in some linear basis B, implying that the signal can be reconstructed accurately using only a small number M ≪ N of basisfunction coefficients associated with B. Compressive sensing ..."
Abstract

Cited by 327 (24 self)
 Add to MetaCart
(Show Context)
The data of interest are assumed to be represented as Ndimensional real vectors, and these vectors are compressible in some linear basis B, implying that the signal can be reconstructed accurately using only a small number M ≪ N of basisfunction coefficients associated with B. Compressive sensing is a framework whereby one does not measure one of the aforementioned Ndimensional signals directly, but rather a set of related measurements, with the new measurements a linear combination of the original underlying Ndimensional signal. The number of required compressivesensing measurements is typically much smaller than N, offering the potential to simplify the sensing system. Let f denote the unknown underlying Ndimensional signal, and g a vector of compressivesensing measurements, then one may approximate f accurately by utilizing knowledge of the (underdetermined) linear relationship between f and g, in addition to knowledge of the fact that f is compressible in B. In this paper we employ a Bayesian formalism for estimating the underlying signal f based on compressivesensing measurements g. The proposed framework has the following properties: (i) in addition to estimating the underlying signal f, “error bars ” are also estimated, these giving a measure of confidence in the inverted signal; (ii) using knowledge of the error bars, a principled means is provided for determining when a sufficient
Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection
 IN CVPR
, 2004
"... We consider the problem of detecting a large number of different object classes in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, which can be slow and require much training data. We present a multiclass boosting procedure (joint boosting) ..."
Abstract

Cited by 311 (17 self)
 Add to MetaCart
We consider the problem of detecting a large number of different object classes in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, which can be slow and require much training data. We present a multiclass boosting procedure (joint boosting) that reduces both the computational and sample complexity, by finding common features that can be shared across the classes. The detectors for each class are trained jointly, rather than independently. For a given performance level, the total number of features required is observed to scale approximately logarithmically with the number of classes. In addition, we find that the features selected by independently trained classifiers are often specific to the class, whereas the features selected by the jointly trained classifiers are more generic features, such as lines and edges.
Selftaught learning: Transfer learning from unlabeled data
 Proceedings of the Twentyfourth International Conference on Machine Learning
, 2007
"... We present a new machine learning framework called “selftaught learning ” for using unlabeled data in supervised classification tasks. We do not assume that the unlabeled data follows the same class labels or generative distribution as the labeled data. Thus, we would like to use a large number of ..."
Abstract

Cited by 295 (20 self)
 Add to MetaCart
(Show Context)
We present a new machine learning framework called “selftaught learning ” for using unlabeled data in supervised classification tasks. We do not assume that the unlabeled data follows the same class labels or generative distribution as the labeled data. Thus, we would like to use a large number of unlabeled images (or audio samples, or text documents) randomly downloaded from the Internet to improve performance on a given image (or audio, or text) classification task. Such unlabeled data is significantly easier to obtain than in typical semisupervised or transfer learning settings, making selftaught learning widely applicable to many practical learning problems. We describe an approach to selftaught learning that uses sparse coding to construct higherlevel features using the unlabeled data. These features form a succinct input representation and significantly improve classification performance. When using an SVM for classification, we further show how a Fisher kernel can be learned for this representation. 1.
Sharing Visual Features for Multiclass And Multiview Object Detection
, 2004
"... We consider the problem of detecting a large number of different classes of objects in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, at multiple locations and scales. This can be slow and can require a lot of training data, since each clas ..."
Abstract

Cited by 278 (6 self)
 Add to MetaCart
We consider the problem of detecting a large number of different classes of objects in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, at multiple locations and scales. This can be slow and can require a lot of training data, since each classifier requires the computation of many different image features. In particular, for independently trained detectors, the (runtime) computational complexity, and the (trainingtime) sample complexity, scales linearly with the number of classes to be detected. It seems unlikely that such an approach will scale up to allow recognition of hundreds or thousands of objects.
Convex multitask feature learning
 MACHINE LEARNING
, 2007
"... We present a method for learning sparse representations shared across multiple tasks. This method is a generalization of the wellknown singletask 1norm regularization. It is based on a novel nonconvex regularizer which controls the number of learned features common across the tasks. We prove th ..."
Abstract

Cited by 250 (25 self)
 Add to MetaCart
(Show Context)
We present a method for learning sparse representations shared across multiple tasks. This method is a generalization of the wellknown singletask 1norm regularization. It is based on a novel nonconvex regularizer which controls the number of learned features common across the tasks. We prove that the method is equivalent to solving a convex optimization problem for which there is an iterative algorithm which converges to an optimal solution. The algorithm has a simple interpretation: it alternately performs a supervised and an unsupervised step, where in the former step it learns taskspecific functions and in the latter step it learns commonacrosstasks sparse representations for these functions. We also provide an extension of the algorithm which learns sparse nonlinear representations using kernels. We report experiments on simulated and real data sets which demonstrate that the proposed method can both improve the performance relative to learning each task independently and lead to a few learned features common across related tasks. Our algorithm can also be used, as a special case, to simply select – not learn – a few common variables across the tasks.
Learning Multiple Tasks with Kernel Methods
 Journal of Machine Learning Research
, 2005
"... Editor: John ShaweTaylor We study the problem of learning many related tasks simultaneously using kernel methods and regularization. The standard singletask kernel methods, such as support vector machines and regularization networks, are extended to the case of multitask learning. Our analysis sh ..."
Abstract

Cited by 248 (10 self)
 Add to MetaCart
(Show Context)
Editor: John ShaweTaylor We study the problem of learning many related tasks simultaneously using kernel methods and regularization. The standard singletask kernel methods, such as support vector machines and regularization networks, are extended to the case of multitask learning. Our analysis shows that the problem of estimating many task functions with regularization can be cast as a single task learning problem if a family of multitask kernel functions we define is used. These kernels model relations among the tasks and are derived from a novel form of regularizers. Specific kernels that can be used for multitask learning are provided and experimentally tested on two real data sets. In agreement with past empirical work on multitask learning, the experiments show that learning multiple related tasks simultaneously using the proposed approach can significantly outperform standard singletask learning particularly when there are many related tasks but few data per task.
Multitask feature learning
 Advances in Neural Information Processing Systems 19
, 2007
"... We present a method for learning a lowdimensional representation which is shared across a set of multiple related tasks. The method builds upon the wellknown 1norm regularization problem using a new regularizer which controls the number of learned features common for all the tasks. We show that th ..."
Abstract

Cited by 240 (8 self)
 Add to MetaCart
(Show Context)
We present a method for learning a lowdimensional representation which is shared across a set of multiple related tasks. The method builds upon the wellknown 1norm regularization problem using a new regularizer which controls the number of learned features common for all the tasks. We show that this problem is equivalent to a convex optimization problem and develop an iterative algorithm for solving it. The algorithm has a simple interpretation: it alternately performs a supervised and an unsupervised step, where in the latter step we learn commonacrosstasks representations and in the former step we learn taskspecific functions using these representations. We report experiments on a simulated and a real data set which demonstrate that the proposed method dramatically improves the performance relative to learning each task independently. Our algorithm can also be used, as a special case, to simply select – not learn – a few common features across the tasks.