Solving weak transduction with EM

Robotics and Autonomous Systems

Volumn 39, Issue 3-4, 2002, Pages 129-143

  Ivanov, Yuri A ^a   Blumberg, Bruce M ^a  

^a MIT MEDIA LAB   (United States)

Author keywords

EM algorithm; Weak transduction; Weakly labeled data

Indexed keywords

ALGORITHMS; AUTONOMOUS AGENTS; FEEDBACK; PARAMETER ESTIMATION; SPEECH RECOGNITION;

WEAK TRANSDUCTION;

ROBOT LEARNING;

EID: 0037199016     PISSN: 09218890     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0921-8890(02)00199-9     Document Type: Conference Paper

References (12)

1. Maximum likelihood from incomplete data via the EM algorithm
2. Reinforcement learning approach to online clustering
3. Tutorial: Expectation-maximization as lower bound maximization
4. A view of the EM algorithm that justifies incremental, sparse and other variants
5. Text classification from labeled and unlabeled documents using EM
6. Mixture densities, maximum likelihood, and the EM algorithm
7. Reinforcement learning by probability matching
8. A new approach to the design of reinforcement schemes for learning automata
9. A class of gradient-estimating algorithms for reinforcement learning in neural networks
10. On convergence properties of the EM algorithm for Gaussian mixtures