منابع مشابه
Learning Recursive Automata from Positive Examples
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...
متن کاملLearning functions from examples
This paper concerns algorithms that "learn functions from examples. Functions on strings of a finite alphabet are considered and the notion of dimensionality defined for families of such functions. Using this notion, a theorem is proved identifying the most general conditions under which a family of functions can be efficiently learned from examples. Turning to some familiar families: we presen...
متن کاملLearning from Order Examples
We advocate a new learning task that deals with orders of items, and we call this the Learning from Order Examples (LOE) task. The aim of the task is to acquire the rule that is used for estimating the proper order of a given unordered item set. The rule is acquired from training examples that are ordered item sets. We present several solution methods for this task, and evaluate the performance...
متن کاملLearning From Snapshot Examples
Examples are a powerful tool for teaching both humans and computers. In order to learn from examples, however, a student must first extract the examples from its stream of perception. Snapshot learning is a general approach to this problem, in which relevant samples of perception are used as examples. Learning from these examples can in turn improve the judgement of the snapshot mechanism, impr...
متن کاملLearning Languages from Examples
In this project I explore the machine learning problem of learning formal languages from positive and negative examples. I describe a technique proposed by Kontorovich, Cortes, and Mohri in their paper titled “Learning Linearly Separable Languages.” The premise of this paper is that there exists a family of languages that are linearly separable and efficiently computable under a certain computa...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Machine Learning
سال: 1991
ISSN: 0885-6125,1573-0565
DOI: 10.1007/bf00114841