Probably approximately correct learning

Known as: Probably approximately correct, PAC Learning, PAC 
In computational learning theory, probably approximately correct learning (PAC learning) is a framework for mathematical analysis of machine learning… (More)
Wikipedia

Topic mentions per year

Topic mentions per year

1972-2017
020406019722017

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
2016
2016
We consider a controller synthesis problem in turnbased stochastic games with both a qualitative linear temporal logic (LTL… (More)
  • figure 1
  • figure 2
  • figure 4
  • figure 5
  • figure 3
Is this relevant?
2015
2015
This paper builds upon earlier work of the authors in formulating the one-bit compressed sensing (OBCS) problem as a problem in… (More)
Is this relevant?
2014
2014
We consider synthesis of controllers that maximize the probability of satisfying given temporal logic specifications in unknown… (More)
  • figure 1
  • table I
  • figure 2
  • figure 3
Is this relevant?
2011
2011
A* is a best-first search algorithm that returns an optimal solution. w-admissible algorithms guarantee that the returned… (More)
  • figure 1
  • table 1
Is this relevant?
2009
2009
We consider the problem of searching a document collection using a set of independent computers. That is, the computers do not… (More)
  • figure 1
  • table 1
  • table 2
  • table 3
Is this relevant?
2008
2008
OF THE DISSERTATION Probably Approximately Correct (PAC) Exploration in Reinforcement Learning by Alexander L. Strehl… (More)
  • figure 1.1
  • figure 1.2
  • figure 1.3
  • figure 4.1
  • figure 4.2
Is this relevant?
2004
2004
In this paper, we study the behaviour of PAC learning algorithms when the input sequence is not i.i.d., but is β-mixing instead… (More)
Is this relevant?
Review
1995
Review
1995
Here we survey some recent theoretical results on the e ciency of machine learning algorithms The main tool described is the… (More)
Is this relevant?
Highly Cited
1987
Highly Cited
1987
The basic question addressed in this paper is: how can a learning algorithm cope with incorrect training examples? Specifically… (More)
Is this relevant?
Highly Cited
1987
Highly Cited
1987
We consider the problem of using queries to learn an unknown concept. Several types of queries are described and studied… (More)
Is this relevant?