We set up a theoretical framework for learning from examples and side information which enables us to compute the tradeoo between the sample complexity and information complexity for learning a target function in a Sobolev functional class F. We use the notion of the n th minimal radius of information of Traub et. al. 23] and combine it with VC-theory to deene a new quantity I n;d (F) which mea...

SUMMARY We present a formalization of an intuitively sound strategy for learning a description from examples : within a partition examples are grouped according to greatest resemblances and examples not in the same subset show a maximum of differences. I. INTRODUCTION WINSTON [4] has demonstrated the importance of the near-miss concept in a context of learning descriptions from examples. His me...

A lightness algorithm that separates surface reflectance from illumination in a Mondrian world is synthesized automatically from a set of examples, pairs of input (image irradiance) and desired output (surface reflectance). The algorithm, which resembles a new lightness algorithm recently proposed by Land, is approximately equivalent to filtering the image through a center-surround receptive fi...

We present an algorithm for automatically constructing a decompositional shape model from examples. Unlike current approaches to structural model acquisition, in which one-to-one correspondences among appearance-based features are used to construct an exemplar-based model, we search for many-tomany correspondences among qualitative shape features (multi-scale ridges and blobs) to construct a ge...

An important property of models constructed through the process of learning from examples is the manipulation and control of the data itself. When the data is actively selected or generated the process is known as exploration. Reeection about the internal model allows exploration to be more than just a random choice in the input space. In this paper we identify two basic forms of reeective expl...

We address the problem of performing semantic transformations on strings, which may represent a variety of data types (or their combination) such as a column in a relational table, time, date, currency, etc. Unlike syntactic transformations, which are based on regular expressions and which interpret a string as a sequence of characters, semantic transformations additionally require exploiting t...

In this theoretical paper, we compare the “classical” learning techniques used to infer regular grammars from positive examples with the ones used to infer categorial grammars. To this aim, we first study how to translate finite state automata into categorial grammars and back. We then show that the generalization operators employed in both domains can be compared, and that their result can alw...

A number of algorithms and its applications for automatic classifiers learning from examples is ever growing. Most of existing algorithms require a training set of completely annotated examples, which are often hard to obtain. In this thesis, we tackle the problem of learning from partially annotated examples, which means that each training input comes with a set of admissible labels only one o...

A lexicon containing explicit mappings between words and pronunciations is an integral part of most automatic speech recognizers (ASRs). While many ASR components can be trained or adapted using data, the lexicon is one of the few that typically remains static until experts make manual changes. This work takes a step towards alleviating the need for manual intervention by integrating a popular ...