Automatic Feature Generation for Problem Solving Systems
نویسندگان
چکیده
Existing methods for constructive induction usually isolate feature generation from problem solving, and do not exploit information about the purpose for which features are created. This paper describes a theory of feature generation that creates features using both a domain theory and feedback from a concept learner. An evaluation function can then be learned using these features that is able to direct a problem-solver. The theory has been implemented in a system called Zenith, which has been applied to two domains. Zenith is able to generate useful features for each domain, given only a domain theory and the ability to solve problems in the domain.
منابع مشابه
Cockpit Crew Pairing Problem in Airline Scheduling: Shortest Path with Resources Constraints Approach
Increasing competition in the air transport market has intensified active airlines’ efforts to keep their market share by attaching due importance to cost management aimed at reduced final prices. Crew costs are second only to fuel costs on the cost list of airline companies. So, this paper attempts to investigate the cockpit crew pairing problem. The set partitioning problem has been used for ...
متن کاملAutomatic Interpretation of UltraCam Imagery by Combination of Support Vector Machine and Knowledge-based Systems
With the development of digital sensors, an increasing number of high-resolution images are available. Interpretation of these images is not possible manually, which necessitates seeking for practical, fast and automatic solutions to solve the environmental and location-based management problems. The land cover classification using high-resolution imagery is a difficult process because of the c...
متن کاملA Proposed Improved Hybrid Hill Climbing Algorithm with the Capability of Local Search for Solving the Nonlinear Economic Load Dispatch Problem
This paper introduces a new hybrid hill-climbing algorithm (HHC) for solving the Economic Dispatch (ED) problem. This algorithm solves the ED problems with a systematic search structure with a global search. It improves the results obtained from an evolutionary algorithm with local search and converges to the best possible solution that grabs the accuracy of the problem. The most important goal...
متن کاملIntelligent Tuned Harmony Search for Solving Economic Dispatch Problem with Valve-point Effects and Prohibited Operating Zones
Economic dispatch with valve point effect and Prohibited Operating Zones (POZs) is a non-convex and discontinuous optimization problem. Harmony Search (HS) is one of the recently presented meta-heuristic algorithms for solving optimization problems, which has different variants. The performances of these variants are severely affected by selection of different parameters of the algorithm. Intel...
متن کاملThe Automatic Generation of Knowledge Spaces From Problem Solving Strategies
In this paper, we explore theoretical and practical aspects of the automatic generation of knowledge spaces from problem solving strategies. We show how the generated spaces can be used for adapting strategy-based problem solving learning environments (PSLEs).
متن کامل