The preferences toward constructivist Internet-based learning environments among university students in Taiwan

Numerous educators have proposed the development of constructivist Internet-based learning environments for students. When creating the constructivist Internet-based learning environments, it is important for researchers to be aware of students’ preferences toward these environments. Through gathering data from 659 university students in Taiwan, this study developed a questionnaire to assess students’ preferences toward constructivist Internet-based learning environments. The questionnaire, with adequate validity and reliability, included 34 items on the following seven scales: relevance, multiple sources (and interpretations), challenge, student negotiation, cognitive apprenticeship, reflective thinking and epistemological awareness. The questionnaire responses revealed that male students tended to prefer the Internet-based learning environments where they could solve challenging problems, acquire cognitive apprenticeship and guidance from experts, and promote epistemological development than did female students. The findings also suggested that, if educators intend to develop Internet-based learning environments for more academically advanced students, such as graduate students, care should be taken to create more opportunities for them to negotiate ideas, obtain proper guidance, reflect their own thoughts, and explore epistemological issues. Finally, students with more Internet experiences tended to demand more on many features of the constructivist Internet-based learning environments than those with less Internet experiences.     

The relationship between learning styles and cognitive traits – Getting additional information for improving student modelling

Student modelling is an important process for adaptive virtual learning environments. Student models include a range of information about the learners such as their domain competence, learning style or cognitive traits. To be able to adapt to the learners’ needs in an appropriate way, a reliable student model is necessary, but getting enough information about a learner is quite challenging. Therefore, mechanisms are needed to support the detection process of the required information. In this paper, we investigate the relationship between learning styles, in particular, those pertaining to the Felder–Silverman learning style model and working memory capacity, one of the cognitive traits included in the cognitive trait model. The identified relationship is derived from links between learning styles, cognitive styles, and working memory capacity which are based on studies from the literature. As a result, we demonstrate that learners with high working memory capacity tend to prefer a reflective, intuitive, and sequential learning style whereas learners with low working memory capacity tend to prefer an active, sensing, visual, and global learning style. This interaction can be used to improve the student model. Systems which are able to detect either only cognitive traits or only learning styles retrieve additional information through the identified relationship. Otherwise, for systems that already incorporate learning styles and cognitive traits, the interaction can be used to improve the detection process of both by including the additional information of a learning style into the detection process of cognitive traits and vice versa. This leads to a more reliable student model.     

Rollout sampling approximate policy iteration

Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervised learning problem. This paper proposes variants of an improved policy iteration scheme which addresses the core sampling problem in evaluating a policy through simulation as a multi-armed bandit machine. The resulting algorithm offers comparable performance to the previous algorithm achieved, however, with significantly less computational effort. An order of magnitude improvement is demonstrated experimentally in two standard reinforcement learning domains: inverted pendulum and mountain-car.     

User simulation in a stochastic dialog system

We present a new methodology of user simulation applied to the evaluation and refinement of stochastic dialog systems. Common weaknesses of these systems are the scarceness of the training corpus and the cost of an evaluation made by real users. We have considered the user simulation technique as an alternative way of testing and improving our dialog system. We have developed a new dialog manager that plays the role of the user. This user dialog manager incorporates several knowledge sources, combining statistical and heuristic information in order to define its dialog strategy. Once the user simulator is integrated into the dialog system, it is possible to enhance the dialog models by an automatic strategy learning. We have performed an extensive evaluation, achieving a slight but clear improvement of the dialog system.     

Boosted Bayesian network classifiers

The use of Bayesian networks for classification problems has received a significant amount of recent attention. Although computationally efficient, the standard maximum likelihood learning method tends to be suboptimal due to the mismatch between its optimization criteria (data likelihood) and the actual goal of classification (label prediction accuracy). Recent approaches to optimizing classification performance during parameter or structure learning show promise, but lack the favorable computational properties of maximum likelihood learning. In this paper we present boosted Bayesian network classifiers, a framework to combine discriminative data-weighting with generative training of intermediate models. We show that boosted Bayesian network classifiers encompass the basic generative models in isolation, but improve their classification performance when the model structure is suboptimal. We also demonstrate that structure learning is beneficial in the construction of boosted Bayesian network classifiers. On a large suite of benchmark data-sets, this approach outperforms generative graphical models such as naive Bayes and TAN in classification accuracy. Boosted Bayesian network classifiers have comparable or better performance in comparison to other discriminatively trained graphical models including ELR and BNC. Furthermore, boosted Bayesian networks require significantly less training time than the ELR and BNC algorithms.     

Transfer in variable-reward hierarchical reinforcement learning

Transfer learning seeks to leverage previously learned tasks to achieve faster learning in a new task. In this paper, we consider transfer learning in the context of related but distinct Reinforcement Learning (RL) problems. In particular, our RL problems are derived from Semi-Markov Decision Processes (SMDPs) that share the same transition dynamics but have different reward functions that are linear in a set of reward features. We formally define the transfer learning problem in the context of RL as learning an efficient algorithm to solve any SMDP drawn from a fixed distribution after experiencing a finite number of them. Furthermore, we introduce an online algorithm to solve this problem, Variable-Reward Reinforcement Learning (VRRL), that compactly stores the optimal value functions for several SMDPs, and uses them to optimally initialize the value function for a new SMDP. We generalize our method to a hierarchical RL setting where the different SMDPs share the same task hierarchy. Our experimental results in a simplified real-time strategy domain show that significant transfer learning occurs in both flat and hierarchical settings. Transfer is especially effective in the hierarchical setting where the overall value functions are decomposed into subtask value functions which are more widely amenable to transfer across different SMDPs.     

Inductive transfer with context-sensitive neural networks

Context-sensitive Multiple Task Learning, or csMTL, is presented as a method of inductive transfer which uses a single output neural network and additional contextual inputs for learning multiple tasks. Motivated by problems with the application of MTL networks to machine lifelong learning systems, csMTL encoding of multiple task examples was developed and found to improve predictive performance. As evidence, the csMTL method is tested on seven task domains and shown to produce hypotheses for primary tasks that are often better than standard MTL hypotheses when learning in the presence of related and unrelated tasks. We argue that the reason for this performance improvement is a reduction in the number of effective free parameters in the csMTL network brought about by the shared output node and weight update constraints due to the context inputs. An examination of IDT and SVM models developed from csMTL encoded data provides initial evidence that this improvement is not shared across all machine learning models.     

Variational Segmentation of Image Sequences Using Region-Based Active Contours and Deformable Shape Priors

In this paper we address the problem of segmentation in image sequences using region-based active contours and level set methods. We propose a novel method for variational segmentation of image sequences containing nonrigid, moving objects. The method is based on the classical Chan-Vese model augmented with a novel frame-to-frame interaction term, which allow us to update the segmentation result from one image frame to the next using the previous segmentation result as a shape prior. The interaction term is constructed to be pose-invariant and to allow moderate deformations in shape. It is expected to handle the appearance of occlusions which otherwise can make segmentation fail. The performance of the model is illustrated with experiments on synthetic and real image sequences.     

Learning to Locate Informative Features for Visual Identification

Object identification is a specialized type of recognition in which the category (e.g. cars) is known and the goal is to recognize an object’s exact identity (e.g. Bob’s BMW). Two special challenges characterize object identification. First, inter-object variation is often small (many cars look alike) and may be dwarfed by illumination or pose changes. Second, there may be many different instances of the category but few or just one positive “training” examples per object instance. Because variation among object instances may be small, a solution must locate possibly subtle object-specific salient features, like a door handle, while avoiding distracting ones such as specular highlights. With just one training example per object instance, however, standard modeling and feature selection techniques cannot be used. We describe an on-line algorithm that takes one image from a known category and builds an efficient “same” versus “different” classification cascade by predicting the most discriminative features for that object instance. Our method not only estimates the saliency and scoring function for each candidate feature, but also models the dependency between features, building an ordered sequence of discriminative features specific to the given image. Learned stopping thresholds make the identifier very efficient. To make this possible, category-specific characteristics are learned automatically in an off-line training procedure from labeled image pairs of the category. Our method, using the same algorithm for both cars and faces, outperforms a wide variety of other methods.     

Efficient Learning of Relational Object Class Models

We present an efficient method for learning part-based object class models from unsegmented images represented as sets of salient features. A model includes parts’ appearance, as well as location and scale relations between parts. The object class is generatively modeled using a simple Bayesian network with a central hidden node containing location and scale information, and nodes describing object parts. The model’s parameters, however, are optimized to reduce a loss function of the training error, as in discriminative methods. We show how boosting techniques can be extended to optimize the relational model proposed, with complexity linear in the number of parts and the number of features per image. This efficiency allows our method to learn relational models with many parts and features. The method has an advantage over purely generative and purely discriminative approaches for learning from sets of salient features, since generative method often use a small number of parts and features, while discriminative methods tend to ignore geometrical relations between parts. Experimental results are described, using some bench-mark data sets and three sets of newly collected data, showing the relative merits of our method in recognition and localization tasks.