We present and analyze an agnostic active learning algorithm that works without keeping a version space. This is unlike all previous approaches where a restricted set of candidate hypotheses is maintained throughout learning, and only hypotheses from this set are ever returned. By avoiding this version space approach, our algorithm sheds the computational burden and brittleness associated with ...

Active Learning is an important branch of Machine Learning that tries to reduce the label complexity associated with the task of constructing classifiers. In this work, we apply two major active learning techniques to the U.S. census income data and demonstrate the superior label complexity of active learning over supervised learning.

In many real-world applications there are usually abundant unlabeled data but the amount of labeled training examples are often limited, since labeling the data requires extensive human effort and expertise. Thus, exploiting unlabeled data to help improve the learning performance has attracted significant attention. Major techniques for this purpose include semi-supervised learning and active l...

background:     purpose:     methods:     results:     conclusion:     key words:     pbl, lecture based method, education, frequent quizzes the variables such as changing the way of learning, using different methods in teaching, showing scientific films in class or, as a whole, active learning have significant effects on the results of final examination. the results showed that by changing the...

In the literature, most prior work on coreference resolution centered on the newswire domain. Although a coreference resolution system trained on the newswire domain performs well on newswire texts, there is a huge performance drop when it is applied to the biomedical domain. In this paper, we present an approach integrating domain adaptation with active learning to adapt coreference resolution...

This article examines the intersection of two drivers in the contemporary higher education environment. First, the increase in blended learning, propelled by advances in computing technology and the drive towards student-centred, active learning pedagogies influenced by social constructivism. Second, the need for university curriculum to become more inclusive as the sector continues to respond ...

This study examines the evidence for the effectiveness of active learning. It defines the common forms of active learning most relevant for engineering faculty and critically examines the core element of each method. It is found that there is broad but uneven support for the core elements of active, collaborative, cooperative and problem-based learning.

Learning to use an object-oriented framework is a hard task. However, little work has been done to develop effective techniques to reduce the effort and time taken to teach how to use a framework. This paper presents an ongoing work on a Case-Based Teaching approach following an active learning process where the learner is involved in resolving exercises based on framework instantiation examples.

This paper shows how a text classifier’s need for labeled training documents can be reduced by taking advantage of a large pool of unlabeled documents. We modify the Query-by-Committee (QBC) method of active learning to use the unlabeled pool for explicitly estimating document density when selecting examples for labeling. Then active learning is combined with ExpectationMaximization in order to...

Multi-label classification, where each instance is assigned to multiple categories, is a prevalent problem in data analysis. However, annotations of multi-label instances are typically more timeconsuming or expensive to obtain than annotations of single-label instances. Though active learning has been widely studied on reducing labeling effort for single-label problems, current research on mult...