In this dissertation, the problem of learning from highly imbalanced data is studied. Imbalance data learning is of great importance and challenge in many real applications. Dealing with a minority class normally needs new concepts, observations and solutions in order to fully understand the underlying complicated models. We try to systematically review and solve this special learning task in t...

I present a new online learning algorithm that extends the exponentiated gradient framework to infinite dimensional spaces. My analysis shows that the algorithm is implicitly able to estimate the L2 norm of the unknown competitor, U , achieving a regret bound of the order of O(U log(U T + 1)) √ T ), instead of the standard O((U + 1) √ T ), achievable without knowing U . For this analysis, I int...

The past twelve years have seen ubiquitous learning (u-learning) emerging as a new learning paradigm based on ubiquitous technology. By integrating a high level of mobility into the learning environment, u-learning enables learning not only through formal but also through informal and social learning modalities. This makes it suitable for lifelong learners that want to explore, identify and sei...

Learning the English past tense is characterized by a U-shaped learning function for the irregular verbs. Existing cognitive models often rely on a sudden increase in vocabulary, a high tokenfrequency of regular verbs, and complicated schemes of feedback in order to model this phenomenon. All these assumptions are at odds with empirical data. In this paper a hybrid ACT-R model is presented that...

This paper addresses the problem of reinforcement learning in continuous domains through teaching by demonstration. Our approach is based on the Continuous U-Tree algorithm, which generates a tree-based discretization of a continuous state space while applying general reinforcement learning techniques. We introduce a method for generating a preliminary state discretization and policy from exper...

Learning the English past tense is characterized by a U-shaped learning function for the irregular verbs. Existing cognitive models rely on a sudden increases in vocabulary, a high token-frequency of regular verbs, and convoluted schemes of feedback in order to model this phenomenon. All these assumptions are at odds with empirical data. In this paper a hybrid ACT-R model is presented that show...