Abstract
Learning can be thought of as the activity which allows the learner to formulate the hypothesis likely to agree with previous observations. New observations might induce the learner to revise previous hypotheses, and thus to modify/improve the current state of knowledge in order to combine the new and the old observations. Observations are usually examples and counterexamples provided “randomly” to the learner. Alternatively, the learner may have the possibility to ask for the correct classification of an example chosen from a given pool. In many concrete applications the learning process is affected by noise. In this chapter we shall discuss several examples of learning in noisy environments, showing their relations to both Ulam-Renyi games and computational learning theories.
Sign-in/Register to access full text options 
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.
