Communications of the ACM
Statistical analysis with missing data
Statistical analysis with missing data
Information Processing Letters
Computational limitations on learning from examples
Journal of the ACM (JACM)
Learnability and the Vapnik-Chervonenkis dimension
Journal of the ACM (JACM)
Prediction-preserving reducibility
Journal of Computer and System Sciences - 3rd Annual Conference on Structure in Complexity Theory, June 14–17, 1988
SIAM Journal on Computing
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
On learning ring-sum-expansions
SIAM Journal on Computing
Efficient distribution-free learning of probabilistic concepts
Journal of Computer and System Sciences - Special issue: 31st IEEE conference on foundations of computer science, Oct. 22–24, 1990
A formal model of hierarchical concept learning
Information and Computation
An introduction to computational learning theory
An introduction to computational learning theory
On learning from noisy and incomplete examples
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Knowing what doesn't matter: exploiting the omission of irrelevant data
Artificial Intelligence - Special issue on relevance
Efficient noise-tolerant learning from statistical queries
Journal of the ACM (JACM)
Learning with restricted focus of attention
Journal of Computer and System Sciences
Artificial Intelligence
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
Machine Learning
Machine Learning
Learning from examples with unspecified attribute values
Information and Computation
Journal of the ACM (JACM)
Autodidactic learning and reasoning
Autodidactic learning and reasoning
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
KES-AMSTA'11 Proceedings of the 5th KES international conference on Agent and multi-agent systems: technologies and applications
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Evolvability via the Fourier transform
Theoretical Computer Science
Implicit learning of common sense for reasoning
IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence
Hi-index | 0.00 |
When sensing its environment, an agent often receives information that only partially describes the current state of affairs. The agent then attempts to predict what it has not sensed, by using other pieces of information available through its sensors. Machine learning techniques can naturally aid this task, by providing the agent with the rules to be used for making these predictions. For this to happen, however, learning algorithms need to be developed that can deal with missing information in the learning examples in a principled manner, and without the need for external supervision. We investigate this problem herein. We show how the Probably Approximately Correct semantics can be extended to deal with missing information during both the learning and the evaluation phase. Learning examples are drawn from some underlying probability distribution, but parts of them are hidden before being passed to the learner. The goal is to learn rules that can accurately recover information hidden in these learning examples. We show that for this to be done, one should first dispense the requirement that rules should always make definite predictions; ''don't know'' is sometimes necessitated. On the other hand, such abstentions should not be done freely, but only when sufficient information is not present for definite predictions to be made. Under this premise, we show that to accurately recover missing information, it suffices to learn rules that are highly consistent, i.e., rules that simply do not contradict the agent's sensory inputs. It is established that high consistency implies a somewhat discounted accuracy, and that this discount is, in some defined sense, unavoidable, and depends on how adversarially information is hidden in the learning examples. Within our proposed learning model we prove that any PAC learnable class of monotone or read-once formulas is also learnable from incomplete learning examples. By contrast, we prove that parities and monotone-term 1-decision lists, which are properly PAC learnable, are not properly learnable under the new learning model. In the process of establishing our positive and negative results, we re-derive some basic PAC learnability machinery, such as Occam's Razor, and reductions between learning tasks. We finally consider a special case of learning from partial learning examples, where some prior bias exists on the manner in which information is hidden, and show how this provides a unified view of many previous learning models that deal with missing information. We suggest that the proposed learning model goes beyond a simple extension of supervised learning to the case of incomplete learning examples. The principled and general treatment of missing information during learning, we argue, allows an agent to employ learning entirely autonomously, without relying on the presence of an external teacher, as is the case in supervised learning. We call our learning model autodidactic to emphasize the explicit disassociation of this model from any form of external supervision.