http://cogprints.org/id/eprint/510 2011-03-11T08:54:01Z info:eu-repo/semantics/descriptiveMetadata Modelling Learning as Modelling Moss, Scott Edmonds, Bruce Artificial Intelligence Machine Learning Philosophy of Science Social Psychology Economists tend to represent learning as a procedure for estimating the parameters of the "correct" econometric model. We extend this approach by assuming that agents specify as well as estimate models. Learning thus takes the form of a dynamic process of developing models using an internal language of representation where expectations are formed by forecasting with the best current model. This introduces a distinction between the form and content of the internal models which is particularly relevant for boundedly rational agents. We propose a framework for such model development which use a combination of measures: the error with respect to past data, the complexity of the model, the cost of finding the model and a measure of the model's specificity The agent has to make various trade-offs between them. A utility learning agent is given as an example. 1994-11 Journal (Paginated) PeerReviewed application/postscript http://cogprints.org/510/1/learningA4.ps application/pdf http://cogprints.org/510/5/learning.pdf Moss, Scott and Edmonds, Bruce (1994) Modelling Learning as Modelling. [Journal (Paginated)] http://cogprints.org/510/ info:eu-repo/semantics/objectFile info:eu-repo/semantics/objectFile info:eu-repo/semantics/humanStartPage