On a Question of Nearly Minimal Identification of Functions
نویسنده
چکیده
Suppose A and B are classes of recursive functions. A is said to be an m-cover (∗-cover) for B, iff for each g ∈ B, there exsits an f ∈ A such that f differs from g on at most m inputs (finitely many inputs). C, a class of recursive functions, is a-immune iff C is infinite and every recursively enumerable subclass of C has a finite a-cover. C is a-isolated iff C is finite or a-immune. Chen [Che81] conjectured that every class of recursive functions that is MEx∗ m -identifiable is ∗-isolated. We refute this conjecture.
منابع مشابه
On a Question About Learning Nearly Minimal Programs
Identification of programs for computable functions from their graphs by algorithmic devices is a well studied problem in learning theory. Freivalds and Chen consider identification of ‘minimal’ and ‘nearly minimal’ programs for functions from their graphs. The present paper solves the following question left open by Chen: Is it the case that for any collection of computable functions, C, such ...
متن کاملConcerning the frame of minimal prime ideals of pointfree function rings
Let $L$ be a completely regular frame and $mathcal{R}L$ be the ring of continuous real-valued functions on $L$. We study the frame $mathfrak{O}(Min(mathcal{R}L))$ of minimal prime ideals of $mathcal{R}L$ in relation to $beta L$. For $Iinbeta L$, denote by $textit{textbf{O}}^I$ the ideal ${alphainmathcal{R}Lmidcozalphain I}$ of $mathcal{R}L$. We show that sending $I$ to the set of minimal prime ...
متن کاملKolmogorov numberings and minimal identification
Identification of programs for computable functions from their graphs by algorithmic devices is a well studied problem in learning theory. Freivalds and Chen consider identification of ‘minimal’ and ‘nearly minimal’ programs for functions from their graphs. To address certain problems in minimal identification for Gödel numberings, Freivalds later considered minimal identification in Kolmogorov...
متن کاملADAPTIVE FUZZY TRACKING CONTROL FOR A CLASS OF PERTURBED NONLINEARLY PARAMETERIZED SYSTEMS USING MINIMAL LEARNING PARAMETERS ALGORITHM
In this paper, an adaptive fuzzy tracking control approach is proposed for a class of single-inputsingle-output (SISO) nonlinear systems in which the unknown continuous functions may be nonlinearlyparameterized. During the controller design procedure, the fuzzy logic systems (FLS) in Mamdani type are applied to approximate the unknown continuous functions, and then, based on the minimal learnin...
متن کاملAn Infinite Class of Functions Identifiable Using Minimal Programs in all Kolmogorov Numberings
Identification of programs for computable functions from their graphs by algorithmic devices is a well studied problem in learning theory. Freivalds and Chen consider identification of ‘minimal’ and ‘nearly minimal’ programs for functions from their graphs. Freivalds showed that there exists a Gödel numbering in which only finite classes of functions can be identified using minimal programs. To...
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:
- Inf. Process. Lett.
دوره 70 شماره
صفحات -
تاریخ انتشار 1999