International Workshop All '86 on Analogical and inductive inference
Probability and plurality for aggregations of learning machines
Information and Computation
Probabilistic inductive inference
Journal of the ACM (JACM)
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
Learning recursive functions from approximations
Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
On the power of learning robustly
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
The Power of Pluralism for Automatic Program Synthesis
Journal of the ACM (JACM)
Robust learning aided by context
Journal of Computer and System Sciences - Eleventh annual conference on computational learning theory&slash;Twelfth Annual IEEE conference on computational complexity
Robust learning: rich and poor
Journal of Computer and System Sciences
Models of Cooperative Teaching and Learning
The Journal of Machine Learning Research
Robust learning of automatic classes of languages
ALT'11 Proceedings of the 22nd international conference on Algorithmic learning theory
Robust learning of automatic classes of languages
Journal of Computer and System Sciences
| Hi-index | 5.23 |
The present work introduces and justifies the notion of hyperrobust learning where one fixed learner has to learn all functions in a given class plus their images under primitive recursive operators. The following are shown: The notion of learnability does not change if the class of primitive recursive operators is replaced by a larger enumerable class of operators. A class is hyperrobustly Ex-learnable iff it is a subclass of a recursively enumerable family of total functions. So, the notion of hyperrobust learning overcomes a problem of the traditional definitions of robustness which either do not preserve learning by enumeration or still permit topological coding tricks for the learning criterion Ex. Hyperrobust BC-learning as well as the hyperrobust version of Ex-learning by teams are more powerful than hyperrobust Ex-learning. The notion of bounded totalty reliable BC-learning is properly between hyperrobust Ex-learning and hyperrobust BC-learning. Furthermore, the bounded totally reliable BC-learnable classes are characterized in terms of infinite branches of certain enumerable families of bounded recursive trees. A class of infinite branches of another family of trees separates hyperrobust BC-learning from totally reliable BC-learning. Furthermore, the notion of hyperrobust learning aided by selected context turns out to be much more restrictive than its counterpart for robust learning.