On learning of functions refutably
نویسندگان
چکیده
Learning of recursive functions refutably informally means that for every recursive function, the learning machine has either to learn this function or to refute it, that is to signal that it is not able to learn it. Three modi of making precise the notion of refuting are considered. We show that the corresponding types of learning refutably are of strictly increasing power, where already the most stringent of them turns out to be of remarkable topological and algorithmical richness. Furthermore, all these types are closed under union, though in different strengths. Also, these types are shown to be different with respect to their intrinsic complexity; two of them do not contain function classes that are “most difficult” to learn, while the third one does. Moreover, we present several characterizations for these types of learning refutably. Some of these characterizations make clear where the refuting ability of the corresponding learning machines comes from and how it can be realized, in general. For learning with anomalies refutably, we show that several results from standard learning without refutation stand refutably. From this we derive some hierarchies for refutable learning. Finally, we prove that in general one cannot trade stricter refutability constraints for more liberal learning criteria. 1 Supported in part by NUS grant number RP3992710. Preprint submitted to Elsevier Science 11 March 2007
منابع مشابه
Learning Recursive Functions Refutably
Learning of recursive functions refutably means that for every recursive function, the learning machine has either to learn this function or to refute it, i.e., to signal that it is not able to learn it. Three modi of making precise the notion of refuting are considered. We show that the corresponding types of learning refutably are of strictly increasing power, where already the most stringent...
متن کاملRefutable Inductive Inference of Recursive Functions
Learning of recursive functions refutably informally means that for every recursive function, the learning machine has either to learn this function or to refute it, that is to signal that it is not able to learn it. Three modi of making precise the notion of refuting are considered. We show that the corresponding types of learning refutably are of strictly increasing power, where already the m...
متن کاملComparison of the effect of neuropsychological therapy, rhythmic movements and cognitive empowerment on the executive functions of students with specific learning disorder
Introduction: The purpose of the present study was to compare the effect of neuropsychological therapy, rhythmic movements and cognitive empowerment on the executive functions of students with specific learning disorder with reading disorder. Methods: The research method was quasi-experimental with pretest-posttest design with control group sample of 48 students with learning disabilities with...
متن کاملComparison of the Effectiveness of Remote Attention and Memory Cognitive Training on Executive Functions and Behavioral Symptoms in Children with Attention Deficit/Hyperactivity Disorder with and without Special Learning Disorder
The aim of this study was to compare the effectiveness of remote Attention and Memory Cognitive Rehabilitation on executive functions and behavioral symptoms in children with attention-deficit/hyperactivity disorder with and without special learning disorder. The method of this study was quasi-experimental with a pretest-posttest design and a control group. The statistical population of all chi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Theor. Comput. Sci.
دوره 298 شماره
صفحات -
تاریخ انتشار 2003