The purpose of this study was to investigate the impact of 2 concept map (CM) learning strategies on Iranian EFL learners’ reading comprehension ability and learner autonomy. To this end, 60 Iranian EFL learners at the preintermediate level of language proficiency were randomly assigned to 2 groups. Both groups received an 8-week instruction: one through teacher-constructed and the other throug...

This paper presents a novel deep learning architecture to classify structured objects in datasets with a large number of visually similar categories. Our model extends the CRF objective function to a nonlinear form, by factorizing the pairwise potential matrix, to learn neighboring-class embedding. The embedding and the classifier are jointly trained to optimize this highly nonlinear CRF object...

We propose an algorithm that uses Gaussian process regression to learn common hidden structure shared between corresponding sets of heterogenous observations. The observation spaces are linked via a single, reduced-dimensionality latent variable space. We present results from two datasets demonstrating the algorithms’s ability to synthesize novel data from learned correspondences. We first show...

Long-living autonomous agents must be able to learn to perform competently in novel environments. One important aspect of competence is the ability to plan, which entails the ability to learn models of the agent’s own actions and their effects on the environment. In this paper we describe an approach to learn action models of environments with continuous-valued spatial states and realistic phys...

Representation learning-based collaborative filtering (CF) methods address the linear relationship of user-items with dot products and cannot study latent nonlinear applied to implicit feedback. Matching function CF directly learn complicated mapping functions that map user-item pairs matching scores, which has limitations in identifying low-rank relationships. To this end, we propose a deep re...