Please use this identifier to cite or link to this item:
|Title:||Robust learning - Rich and poor|
|Citation:||Case, J., Jain, S., Stephan, F., Wiehagen, R. (2004). Robust learning - Rich and poor. Journal of Computer and System Sciences 69 (2) : 123-165. ScholarBank@NUS Repository. https://doi.org/10.1016/j.jcss.2003.10.005|
|Abstract:||A class script C sign of recursive functions is called robustly learnable in the sense I (where I is any success criterion of learning) if not only script C sign itself but even all transformed classes Θscript C sign), where Θ is any general recursive operator, are learnable in the sense I. It was already shown before, see Fulk (in: 31st Annual IEEE Symposium on Foundation of Computer Science, IEEE Computer Soc. Press, Silver Spring, MD 1990, pp. 405-410), Jain et al. (J. Comput. System Sci. 62 (2001) 178), that for I=Ex (learning in the limit) robust learning is rich in that there are classes being both not contained in any recursively enumerable class of recursive functions and, nevertheless, robustly learnable. For several criteria I, the present paper makes much more precise where we can hope for robustly learnable classes and where we cannot. This is achieved in two ways. First, for I=Ex, it is shown that only consistently learnable classes can be uniformly robustly learnable. Second, some other learning types I are classified as to whether or not they contain rich robustly learnable classes. Moreover, the first results on separating robust learning from uniformly robust learning are derived. © 2003 Elsevier Inc. All rights reserved.|
|Source Title:||Journal of Computer and System Sciences|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Jun 16, 2018
WEB OF SCIENCETM
checked on May 16, 2018
checked on Jun 2, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.