Sciweavers

6 search results - page 1 / 2
» Towards Representation Independence in PAC Learning
Sort
View
AII
1989
13 years 9 months ago
Towards Representation Independence in PAC Learning
In the recent development ofwrious models of learning inspired by the PAC learning model (introduced by Valiant) there has been a trend towards models which are as representation ...
Manfred K. Warmuth
ICML
1999
IEEE
14 years 5 months ago
Simple DFA are Polynomially Probably Exactly Learnable from Simple Examples
E cient learning of DFA is a challenging research problem in grammatical inference. Both exact and approximate (in the PAC sense) identi ability of DFA from examples is known to b...
Rajesh Parekh, Vasant Honavar
NIPS
2001
13 years 6 months ago
Constructing Distributed Representations Using Additive Clustering
If the promise of computational modeling is to be fully realized in higherlevel cognitive domains such as language processing, principled methods must be developed to construct th...
Wheeler Ruml
ICASSP
2010
IEEE
13 years 5 months ago
Towards multi-speaker unsupervised speech pattern discovery
In this paper, we explore the use of a Gaussian posteriorgram based representation for unsupervised discovery of speech patterns. Compared with our previous work, the new approach...
Yaodong Zhang, James R. Glass
SIAMCOMP
2011
12 years 12 months ago
The Chow Parameters Problem
Abstract. In the 2nd Annual FOCS (1961), Chao-Kong Chow proved that every Boolean threshold function is uniquely determined by its degree-0 and degree-1 Fourier coefficients. These...
Ryan O'Donnell, Rocco A. Servedio