Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

9

COLT
1991
Springer

favoriteEmaildiscussreport

128views Machine Learning» more COLT 1991»

Improved Learning of AC0 Functions

13 years 8 months ago

Improved Learning of AC0 Functions

Download www.cs.dartmouth.edu

Two extensions of the Linial, Mansour, Nisan AC0 learning algorithm are presented. The LMN method works when input examples are drawn uniformly. The new algorithmsimprove on theirs by performing well when given inputs drawn from unknown, mutually independent distributions. A variant of the one of the algorithms is conjectured to work in an even broader setting.

Merrick L. Furst, Jeffrey C. Jackson, Sean W. Smit

Real-time Traffic

COLT 1991 | Input Examples | LMN Method | Machine Learning | Mutually Independent |

claim paper

Related Content

» Learning and Lower Bounds for AC0 with Threshold Gates

» Discrepancy and the Power of Bottom Fanin in Depththree Circuits

» Weakly learning DNF and characterizing statistical query learning using Fourier analysis

» Uniform Direct Product Theorems Simplified Optimized and Derandomized

» From Secrecy to Soundness Efficient Verification via Secure Computation

» Tracking value function dynamics to improve reinforcement learning with piecewise linear f...

» Improving Functionalities in a Multiagent Architecture for Ocean Monitoring

» Improved Guarantees for Learning via Similarity Functions

» Beyond local optimality An improved approach to hybrid model learning

Post Info
More Details (n/a)

Added	27 Aug 2010
Updated	27 Aug 2010
Type	Conference
Year	1991
Where	COLT
Authors	Merrick L. Furst, Jeffrey C. Jackson, Sean W. Smith

Comments (0)