Results 1  10
of
30
Learnability and the VapnikChervonenkis dimension
, 1989
"... Valiant’s learnability model is extended to learning classes of concepts defined by regions in Euclidean space E”. The methods in this paper lead to a unified treatment of some of Valiant’s results, along with previous results on distributionfree convergence of certain pattern recognition algorith ..."
Abstract

Cited by 727 (22 self)
 Add to MetaCart
, and the necessary and sufftcient conditions are provided for feasible learnability.
Feasible Learnability of Formal Grammars and The Theory of Natural Language Acquisition
, 1988
"... l of linguistic theory, then, is [o &aracterize this set of possible graalmars, hy specifiying the constraints ogen called the "Universal (Irarerum'". The theory of inductiw inlrence offers a precise solntion to this problem, by characl,erizing exactly what collections of (or its ..."
Abstract

Cited by 8 (2 self)
 Add to MetaCart
to the techuok)gical counterpart of such a problem. In [his paper, we investigate the learuability of formal grammars for linguistic description with respect to a complexity heoretic notioa of feasible learnability called 'polyuomial learnability '. Polynomial learnabillty was originally developed
2. Feasible Learnability of Sets 3. Learning Sets with Onesided Error 4. TimeComplexity Issues in Learning Sets
, 1989
"... ..."
Polynomial learnability and locality of formal grammars
 In 26th Meeting of A.C.L
, 1988
"... We apply a complexity theoretic notion of feasible learnability called "polynomial learnabillty " to the evaluation of grammatical formalisms for linguistic description. We show that a novel, nontriviai constraint on the degree of ~locMity " of grammars allows not only context free la ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
We apply a complexity theoretic notion of feasible learnability called "polynomial learnabillty " to the evaluation of grammatical formalisms for linguistic description. We show that a novel, nontriviai constraint on the degree of ~locMity " of grammars allows not only context free
An Experimental Study of the Learnability of Congestion Control
"... When designing a distributed network protocol, typically it is infeasible to fully define the target network where the protocol is intended to be used. It is therefore natural to ask: How faithfully do protocol designers really need to understand the networks they design for? What are the importan ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
When designing a distributed network protocol, typically it is infeasible to fully define the target network where the protocol is intended to be used. It is therefore natural to ask: How faithfully do protocol designers really need to understand the networks they design for? What
Proceedings of the TwentySecond International Joint Conference on Artificial Intelligence Causal Learnability
"... The ability to predict, or at least recognize, the state of the world that an action brings about, is a central feature of autonomous agents. We propose, herein, a formal framework within which we investigate whether this ability can be autonomously learned. The framework makes explicit certain prem ..."
Abstract
 Add to MetaCart
learning is or is not feasible. Despite the very strong negative learnability results that we obtain, we also identify interesting special cases where learning is feasible and useful. 1
On the Learnability of Causal Domains: Inferring Temporal Reality from Appearances
 In Working notes of the 8th International Symposium on Logical Formalizations of Commonsense Reasoning (Commonsense’07
, 2007
"... We examine the feasibility of learning causal domains by observing transitions between states as a result of taking certain actions. We take the approach that the observed transitions are only a macrolevel manifestation of the underlying microlevel dynamics of the environment, which an agent does ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
We examine the feasibility of learning causal domains by observing transitions between states as a result of taking certain actions. We take the approach that the observed transitions are only a macrolevel manifestation of the underlying microlevel dynamics of the environment, which an agent
2007b) "Solving Learnability Problems in the Acquisition of Semantics," Ms
, 1962
"... This paper proposes solutions to two semantic learnability problems that have featured prominently in the literature on language acquisition. Both problems have often been deemed unsolvable for language learners as a matter of logic, and they have accordingly been taken to motivate principles making ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
This paper proposes solutions to two semantic learnability problems that have featured prominently in the literature on language acquisition. Both problems have often been deemed unsolvable for language learners as a matter of logic, and they have accordingly been taken to motivate principles
Dynamically Delayed Postdictive Completeness and Consistency in Learning
, 2008
"... In computational function learning in the limit, an algorithmic learner tries to find a program for a computable function g given successively more values of g, each time outputting a conjectured program for g. A learner is called postdictively complete iff all available data is correctly postdicted ..."
Abstract
 Add to MetaCart
and in other graphs disallowing computable infinitely descending counts. We extend many of the theorems of Akama and Zeugmann and provide some feasible learnability results. Regarding fairness in feasible learning, one needs to limit use of tricks that postpone output hypotheses until there is enough time
Michael Kearns Harvard University Recent Results on Boolean Concept Learning
"... Recently, a new formal model of learnability was introduced [23]. The model is applicable to practical learning systems because it requires the learning algorithm to be feasibly computable, yet at the same time demands only that the algorithm nd an approximation to the unknown rule. We survey recent ..."
Abstract
 Add to MetaCart
Recently, a new formal model of learnability was introduced [23]. The model is applicable to practical learning systems because it requires the learning algorithm to be feasibly computable, yet at the same time demands only that the algorithm nd an approximation to the unknown rule. We survey
Results 1  10
of
30