Hill - Climbing Theories of Learning
نویسنده
چکیده
Much human learning appears to be gradual and unconscious, suggesting a very limited form of search through the space of hypotheses. We propose hill climbing as a framework for such learning and consider a number of systems that learn in this manner. We focus on CLASSIT, a model of concept formation that incrementally acquires a conceptual hierarchy, and MAGGIE, a model of skill improvement that alters motor schemas in response to errors. Both models integrate the processes of learning and performance. Uf, Iie C 9
منابع مشابه
Finding Accurate Fro A Knowledge-Intensive
An approach to analytic learning is described that searches for accurate entailments of a Horn Clause domain theory. A hill-climbing search, guided by an information based evaluation function, is performed by applying a set of operators that derive frontiers from domain theories. The analytic learning system is one component of a multi-strategy relational learning system. We compare the accurac...
متن کاملFinding Accurate Frontiers: A Knowledge-Intensive Approach to Relational Learning
An approach to analytic learning is described that searches for accurate entailments of a Horn Clause domain theory. A hill-climbing search, guided by an information based evaluation function, is performed by applying a set of operators that derive frontiers from domain theories. The analytic learning system is one component of a multi-strategy relational learning system. We compare the accurac...
متن کاملComparison of Genetic and Hill Climbing Algorithms to Improve an Artificial Neural Networks Model for Water Consumption Prediction
No unique method has been so far specified for determining the number of neurons in hidden layers of Multi-Layer Perceptron (MLP) neural networks used for prediction. The present research is intended to optimize the number of neurons using two meta-heuristic procedures namely genetic and hill climbing algorithms. The data used in the present research for prediction are consumption data of water...
متن کاملLearning Relations by Bathfinding
First-order learning systems (e.g., FOlL, FOCL, FORTE) generally rely on hill-climbing heuristics in order to avoid the combinatorial explosion inherent in learning first-order concepts. However, hill-climbing leaves these systems vulnerable to local maxima and local plateaus. We present a method, called relational pathfinding, which has proven highly effective in escaping local maxima and cros...
متن کاملAutomated Reenement of First-order Horn-clause Domain Theories 1
Knowledge acquisition is a diicult, error-prone, and time-consuming task. The task of automatically improving an existing knowledge base using learning methods is addressed by the class of systems performing theory reenement. This paper presents a system, Forte (First-Order Revision of Theories from Examples), which reenes rst-order Horn-clause theories by integrating a variety of diierent revi...
متن کامل