Abstract
The knowledge acquisition process of many Machine Learning approaches is idealized with respect to the exclusion of noisy data, the applicability of backtracking methods, or the arrangement of training examples by a teacher. This paper describes the consequence that arises if the idealization must be abandoned: the system may be led to a dead end. Some tentative ideas are presented as to how a system should react when an increasing number of counter examples arise by the developing a new “paradigm” that must be introduced contrainductively (that is, against well supported hypotheses and factual knowledge).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
