U-shaped learning deals with a learner first having the correct hypothesis, then changing it to an incorrect hypothesis and then relearning the correct hypothesis. This phenomenon has been observed by psychologists in various studies of children development. In this survey talk, we will discuss some recent results regarding U-shaped learning and related crtieria.

We study the problem of approximating and learning coverage functions. A function c : 2 → R is a coverage function, if there exists a universe U with non-negative weights w(u) for each u ∈ U and subsets A1, A2, . . . , An of U such that c(S) = ∑ u∈∪i∈SAi w(u). Alternatively, coverage functions can be described as non-negative linear combinations of monotone disjunctions. They are a natural subc...

We study the problem of approximating and learning coverage functions. A function c : 2 → R is a coverage function, if there exists a universe U with non-negative weights w(u) for each u ∈ U and subsets A1, A2, . . . , An of U such that c(S) = ∑ u∈∪i∈SAi w(u). Alternatively, coverage functions can be described as non-negative linear combinations of monotone disjunctions. They are a natural subc...

This paper reported the results of a study that aimed to construct a sensor and handheld augmented reality (AR)-supported ubiquitous learning (u-learning) environment called the Handheld English Language Learning Organization (HELLO), which is geared towards enhancing students’ language learning. The HELLO integrates sensors, AR, ubiquitous computing and information technologies. It is composed...

The prosperous development of wireless communication and sensor technologies has attracted the attention of researchers from both computer and education fields. Various investigations have been made for applying the new technologies to education purposes, such that more active and adaptive learning activities can be conducted in the real world. Nowadays, ubiquitous learning (u-learning) has bec...

We aim at an extension of AdaBoost to U-Boost, in the paradigm to build a stronger classification machine from a set of weak learning machines. A geometric understanding of the Bregman divergence defined by a generic convex function U leads to the U-Boost method in the framework of information geometry extended to the space of the finite measures over a label set. We propose two versions of U-B...

This paper deenes a new computational model of inductive learning, called U-learnability (Universal Learnability), that is well-suited for rich representation languages, most notably for universal (Turing equivalent) representations. It is motivated by three observations. Firstly, existing computational models of inductive learning|the best known of which are identiication in the limit and PAC-...

The class of shuffle ideals is a fundamental sub-family of regular languages. The shuffle ideal generated by a string set U is the collection of all strings containing some string u ∈ U as a (not necessarily contiguous) subsequence. In spite of its apparent simplicity, the problem of learning a shuffle ideal from given data is known to be computationally intractable. In this paper, we study the...