Sciweavers

1110 search results - page 96 / 222
» An Intelligent Lessons Learned Process
Sort
View
AAAI
2006
14 years 18 days ago
Using Homomorphisms to Transfer Options across Continuous Reinforcement Learning Domains
We examine the problem of Transfer in Reinforcement Learning and present a method to utilize knowledge acquired in one Markov Decision Process (MDP) to bootstrap learning in a mor...
Vishal Soni, Satinder P. Singh
AIM
1999
13 years 11 months ago
JAIR at Five
The Journal of Artificial Intelligence Research (JAIR) was one of the first scientific journals distributed over the Web. It has now completed over five years of successful public...
Steven Minton, Michael P. Wellman
IDA
2010
Springer
13 years 9 months ago
Multi-dimensional data construction method with its application to learning from small-sample-sets
Insufficient training data is one of the major problems in neural network learning, because it leads to poor learning performance. In order to enhance an intelligent learning proc...
Hsiao-Fan Wang, Chun-Jung Huang
SIGUCCS
2003
ACM
14 years 4 months ago
Achieving rapid service deployment in an academic environment
Rapid product or service deployment is most commonly thought of in the corporate, rather than academic, environment. Utilizing a rapid deployment process and a number of highly de...
Shea Nangle
KDD
2010
ACM
233views Data Mining» more  KDD 2010»
14 years 3 months ago
Evolutionary hierarchical dirichlet processes for multiple correlated time-varying corpora
Mining cluster evolution from multiple correlated time-varying text corpora is important in exploratory text analytics. In this paper, we propose an approach called evolutionary h...
Jianwen Zhang, Yangqiu Song, Changshui Zhang, Shix...