Machine Learning - Special issue on inductive transfer
Robust learning aided by context
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Machine Learning for the Detection of Oil Spills in Satellite Radar Images
Machine Learning - Special issue on applications of machine learning and the knowledge discovery process
Forgetting Exceptions is Harmful in Language Learning
Machine Learning - Special issue on natural language learning
IRAL '00 Proceedings of the fifth international workshop on on Information retrieval with Asian languages
Automatic Construction of Decision Trees from Data: A Multi-Disciplinary Survey
Data Mining and Knowledge Discovery
Automatic Lexical Stress Assignment of Unknown Words for Highly Inflected Slovenian Language
TSD '02 Proceedings of the 5th International Conference on Text, Speech and Dialogue
Learning Intermediate Concepts
ALT '01 Proceedings of the 12th International Conference on Algorithmic Learning Theory
Divide and Conquer Machine Learning for a Genomics Analogy Problem (Progress Report)
DS '01 Proceedings of the 4th International Conference on Discovery Science
A comparative assessment of classification methods
Decision Support Systems
Benefitting from the variables that variable selection discards
The Journal of Machine Learning Research
Construction of supervised and unsupervised learning systems for multilingual text categorization
Expert Systems with Applications: An International Journal
Automatic accentuation of words for Slovenian TTS system
SIP'06 Proceedings of the 5th WSEAS international conference on Signal processing
Hi-index | 0.00 |
The performance of the error backpropagation (BP) and ID3 learning algorithms was compared on the task of mapping English text to phonemes and stresses. Under the distributed output code developed by Sejnowski and Rosenberg, it is shown that BP consistently out-performs ID3 on this task by several percentage points. Three hypotheses explaining this difference were explored: (a) ID3 is overfitting the training data, (b) BP is able to share hidden units across several output units and hence can learn the output units better, and (c) BP captures statistical information that ID3 does not. We conclude that only hypothesis (c) is correct. By augmenting ID3 with a simple statistical learning procedure, the performance of BP can be closely matched. More complex statistical procedures can improve the performance of both BP and ID3 substantially in this domain.