RESEARCH ON SELF-ORGANIZING MACHINES.
STANFORD RESEARCH INST MENLO PARK CALIF
Pagination or Media Count:
This report reviews the results of a program of research on self-organizing machines. This research was primarily directed at establishing the conditions under which iterative machine-learning procedures can be guaranteed to converge. The most significant result of this effort was the development of a fairly complete theory of the linear machine, an important trainable multicategory pattern classifier. Theoretical results are summarized and related to the present state of research in pattern recognition. Author
- Information Science