Full-text

URL: ftp://ftp.cs.wisc.edu/machine-learning/s...up/ml95w1/jain.ps.gz

Cached: PDF-161K    PS-302K    PS.gz-68K

SAVE AS an easy-to-recall long filename:

Filename format: author--year--title   PDF-161K    PS-68K    :: About GZip'd PS

Filename format: author--year--title--journal|proceedings|...--pages   PDF-161K    PS-68K

Related links

CiteSeer: http://citeseer.ist.psu.edu/173118.html

Web search: Google Web Search   ::   Google Scholar

Within this site: Cited by (1)    References (17)

Paper at a Glance

Team Learning of Formal Languages
Sanjay Jain
Dept. of Info. Systems & Computer Science
National University of Singapore
Singapore 0511, Republic of Singapore
sanjay@iscs.nus.sg
Arun Sharma
School of Computer Science and Engineering
The University of New South Wales
Sydney, NSW 2052, Australia
arun@cse.unsw.edu.au

Abstract A team of learning machines is a multiset of learning machines. A team is said to success­ fully learn a concept just in case each member of some nonempty subset, of predetermined size, of the team learns the concept. Team learning of computer programs for computable functions from their graphs has been studied extensively. However, team learning of languages turns out to be a more suitable theoretical model for studying computational limits on multi­agent machine learning. The main reason for this is that language learning can model both learning from positive data and learning from positive and negative data, whereas function learning models only learning from positive and neg­ ative data. Some theoretical results about learnability of formal languages by teams of algorithmic ma­ chines are surveyed. Some new results about restricted classes of languages are presented. These results are mainly about two issues: re­ dundancy and aggregation. The issue of re­ dundancy deals with the impact of increasing the size of a team and increasing the number of machines required to be successful. The issue of aggregation deals with conditions un­ der which a team may be replaced by a single machine without any loss in learning ability. Scenarios which can be modeled by team learning are also presented.
1 INTRODUCTION Algorithmic identification in the limit of two concept classes, computable functions and recursively enumer­ able languages, have been studied extensively in the computational learning theory literature. We first describe the learning of a computable func­ tion. A learning machine is fed the graph of a com­ putable function, and the machine, ...

@inproceedings{jain95teamLearning,
  author={Sanjay Jain and Arun Sharma},
  title={Team learning of formal languages},
  year={1995},
  address={Tahoe City, CA},
  editor={Diana Gordon},
  booktitle={Working Notes of the ICML'95 Workshop on Agents that Learn from Other Agents},
  url={http://www.isrl.uiuc.edu/~amag/langev/paper/jain95teamLearning.html}
}

HOME   ::  Conference List   ::   Conference Paper	Comments to: junwang4 you-know-at gmail.com	Last update: 2/2/08