The Structure-Mapping Engine
نویسندگان
چکیده
This paper describes the Structure-Mapping Engine (SME), a cognitive simulation program for studying human analogical processing. SME is based on Gentner’s Structure-Mapping theory of analogy, and provides a “tool kit” for constructing matching algorithms consistent with this theory. This flexibility enhances cognitive simulation studies by simplifying experimentation. Furthermore, SUE is very efficient, making it a candidate component for machine learning systems as well. We review the StructureMapping theory and describe the design of the engine. Next we demonstrate some examples of its operation. Finally, we discuss our plans for using SME in cognitive simulation studies.
منابع مشابه
The Structure-Mapping Engine: Algorithm and Examples
This paper describes the Structure-Mapping Engine (SME), a program for studying analogical processing. SME has been built to explore Gentner's Structure-mapping theory of analogy, and provides a \tool kit" for constructing matching algorithms consistent with this theory. Its exibility enhances cognitive simulation studies by simplifying experimentation. Furthermore, SME is very e cient, making ...
متن کاملApplications and Benefits of Curriculum Mapping: a Systematic Review of International Documents
Introduction: Maps can create a deeper insight of our surrounding environment. The map can also be used in curriculum for its reforming, and developing and ultimately improving teaching-learning process. This systematic review aimed to identify applications and benefits of curriculum mapping. Methods: Seven search engine and websites were searched using the keywords including curriculum mappin...
متن کاملA comparison of different network based modeling methods for prediction of the torque of a SI engine equipped with variable valve timing
Nowadays, due to increasing the complexity of IC engines, calibration task becomes more severe and the need to use surrogate models for investigating of the engine behavior arises. Accordingly, many black box modeling approaches have been used in this context among which network based models are of the most powerful approaches thanks to their flexible structures. In this paper four network base...
متن کاملAir-Fuel Ratio Control of a Lean Burn SI Engine Using Fuzzy Self Tuning Method
Reducing the exhaust emissions of an spark ignition engine by means of engine modifications requires consideration of the effects of these modifications on the variations of crankshaft torque and the engine roughness respectively. Only if the roughness does not exceed a certain level the vehicle do not begin to surge. This paper presents a method for controlling the air-fuel ratio for a lean bu...
متن کاملValue-Function-Based Transfer for Reinforcement Learning Using Structure Mapping
Transfer learning concerns applying knowledge learned in one task (the source) to improve learning another related task (the target). In this paper, we use structure mapping, a psychological and computational theory about analogy making, to find mappings between the source and target tasks and thus construct the transfer functional automatically. Our structure mapping algorithm is a specialized...
متن کامل