An Introduction to Computational Learning Theory

@inproceedings{Kearns1994AnIT,
  title={An Introduction to Computational Learning Theory},
  author={Michael Kearns and Umesh V. Vazirani},
  year={1994}
}
The probably approximately correct learning model Occam's razor the Vapnik-Chervonenkis dimension weak and strong learning learning in the presence of noise inherent unpredictability reducibility in PAC learning learning finite automata by experimentation appendix - some tools for probabilistic analysis. 
On the Learnability of Hidden Markov Models
A simple result is presented that links the learning of hidden Markov models to results in complexity theory about nonlearnability of finite automata under certain cryptographic assumptions. Rather
SIGACT News Complexity Theory Column 95
This paper surveys quantum learning theory: the theoretical aspects of machine learning using quantum computers. We describe the main results known for three models of learning: exact learning from
On Universal Learning Algorithms
We observe that there exists a universal learning algorithm that PAC-learns every concept class within complexity that is linearly related to the complexity of the best learning algorithm for this
A Survey of Quantum Learning Theory
TLDR
The main results known for three models of learning are described: exact learning from membership queries, and Probably Approximately Correct (PAC) and agnostic learning from classical or quantum examples.
Complexity of Equivalence and Learning for Multiplicity
We consider the query and computational complexity of learning multiplicity tree automata in Angluin’s exact learning model. In this model, there is an oracle, called the Teacher, that can answer
Learning Regular Sets with an Incomplete Membership Oracle
This paper gives an "efficient" algorithm for learning deterministic finite automata by using an equivalence oracle and an incomplete membership oracle. This solves an open problem that was posed by
Guest Column: A Survey of Quantum Learning Theory
TLDR
The main results known for three models of learning are described: exact learning from membership queries, and Probably Approximately Correct (PAC) and agnostic learning from classical or quantum examples.
On PAC Learning Algorithms for Rich Boolean Function Classes
We survey the fastest known algorithms for learning various expressive classes of Boolean functions in the Probably Approximately Correct (PAC) learning model.
The sample complexity and computational complexity of Boolean function learning
This report surveys some key results on the learning of Boolean functions in a probabilistic model that is a generalization of the well-known ‘PAC’ model. A version of this is to appear as a chapter
L Algorithms for Learning Finite Automata from Queries: a Unied View
In this survey we compare several known variants of the algorithm for learning deterministic nite automata via membership and equivalence queries. We believe that our presentation makes it easier to
...
1
2
3
4
5
...