Mistake bounds and logarithmic linear-threshold learning algorithms
Mistake bounds and logarithmic linear-threshold learning algorithms
Probably approximate learning of sets and functions
SIAM Journal on Computing
Learning binary relations and total orders
SIAM Journal on Computing
The Power of Self-Directed Learning
Machine Learning
Journal of Computer and System Sciences
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Being taught can be faster than asking questions
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Journal of Computer and System Sciences
On space-bounded learning and the vapnik-chervonenkis dimension
On space-bounded learning and the vapnik-chervonenkis dimension
Recent Developments in Algorithmic Teaching
LATA '09 Proceedings of the 3rd International Conference on Language and Automata Theory and Applications
Recursive teaching dimension, learning complexity, and maximum classes
ALT'10 Proceedings of the 21st international conference on Algorithmic learning theory
Teaching randomized learners with feedback
Information and Computation
Teaching memoryless randomized learners without feedback
ALT'06 Proceedings of the 17th international conference on Algorithmic Learning Theory
DNF are teachable in the average case
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Teaching classes with high teaching dimension using few examples
COLT'05 Proceedings of the 18th annual conference on Learning Theory
| Hi-index | 0.00 |
We consider the self-directed learning model [7] which is a variant of Littlestone's mistake-bound model [9,10]. We will refute the conjecture of [8,2] that for intersection-closed concept classes, the selfdirected learning complexity is related to the VC-dimension. We show that, even under the assumption of intersection-closedness, both parameters are completely incomparable. We furthermore investigate the structure of intersection-closed concept classes which are difficult to learn in the self-directed learning model. We show that such classes must contain maximum classes. We consider the teacher-directed learning model [5] in the worst, best and average case performance. While the teaching complexity in the worst case is incomparable to the VC-dimension, large concept classes (e.g. balls) are bounded by VC-dimension with respect to the average case. We show that the teaching complexity in the best case is bounded by the self-directed learning complexity. It is also bounded by the VC-dimension, if the concept class is intersection-closed. This does not hold for arbitrary concept classes. We find examples which substantiate this gap.