efficient convergence to a correct grammar. We discuss implications for learning from overt data only, as well as other learning issues. We argue that Optimality Theory promotes confluence of the demands of more effective learnability and deeper linguistic explanation.

procedure for a rate of convergence which succeeds after at most B(a)-many mind changes. This (B, L)-learnability provides quantitative information strictly in between a full rate of convergence (obtainable in general only from semi-constructive proofs) and a rate of metastability in the sense of Tao

(or "agnostic") framework. Furthermore, we show a characterization of learnability in the probabilistic concept model, solving an open problem posed by Kearns and Schapire. These results show that the accuracy parameter plays a crucial role in determining the effective complexity

Naive Bayes is an efficient and effective learning algorithm, but previous results show that its representation ability is severely limited since it can only represent certain linearly separable functions in the binary domain. We give necessary and sufficient conditions on linearly separable

and Smolensky (1993, 1996, 1998, 2000), which initiated the learnability research program for Optimality Theory. We argue that the Gradual Learning Algorithm has a number of special advantages: it can learn free variation, deal effectively with noisy learning data, and account for gradient wellformedness

Measure and category (or rather, their recursion-theoretical counterparts) have been used in theoretical computer science to make precise the intuitive notion "for most of the recursive sets." We use the notions of effective measure and category to discuss the relative sizes of inferrible

restricted conditions. The approach exploits image transformations that are specific to the relevant object class, and learnable from example views of other “prototypical ” objects of the same class. In this paper, we introduce such a technique by extending the notion of linear class proposed by Poggio

in designing an annotation scheme. We present a methodology for syntactic selection and apply it to six central dependency structures. Our methodology compares pairs of annotation schemes that differ in the annotation of a single structure. It selects the more learnable scheme, namely the one that can

We study pool-based active learning in the presence of noise, i.e. the agnostic setting. Previous works have shown that the effectiveness of agnostic active learning depends on the learning problem and the hypothesis space. Although there are many cases on which active learning is very useful

The main purpose of this paper is to briefly review some empirical findings on the processing mechanisms of skilled readers and beginning readers in Chinese and English and to compare the learnability of reading in the two languages. In the learning processes, a similar global