An introduction to computational learning theory
An introduction to computational learning theory
Temporal difference learning and TD-Gammon
Communications of the ACM
Neural networks for pattern recognition
Neural networks for pattern recognition
Neuro-Dynamic Programming
| Hi-index | 0.00 |
Machine learning is the study of methods for constructing and improving software systems by analyzing examples of their desired behavior rather than by directly programming them. Machine learning methods are appropriate in application settings where people are unable to provide precise specifications for desired program behavior, but where examples of this behavior are available. Such situations include optical character recognition (q.v.), handwriting recognition, speech recognition (q.v.), automated steering of automobiles, and robot control and navigation. A key property of these tasks is that people can perform them quite easily, but cannot articulate exactly how they perform them. Hence, people can provide input-output examples, but they cannot provide precise specifications or algorithms.