DELTA RULE 2)
← Back
In parallel processing networks, "A learning rule that utilizes the discrepancy between the desired and actual output of each output unit to change the weigths feeding into it" (W. BECHTEL & A. ABRAHAMSON, 1991, p. 306).
"It is also known as the WIDROW-HOFF rule and the least mean squares rule" (p.306).
This amounts to an adaptive process based on feedbacks and is the basic tool for the progressive betterment of the efficiency of the learning network.
Categories
- 1) General information
- 2) Methodology or model
- 3) Epistemology, ontology and semantics
- 4) Human sciences
- 5) Discipline oriented
Publisher
Bertalanffy Center for the Study of Systems Science(2020).
To cite this page, please use the following information:
Bertalanffy Center for the Study of Systems Science (2020). Title of the entry. In Charles François (Ed.), International Encyclopedia of Systems and Cybernetics (2). Retrieved from www.systemspedia.org/[full/url]
We thank the following partners for making the open access of this volume possible: