creators_name: Ghirlanda, Stefano creators_name: Enquist, Magnus type: journalp datestamp: 2006-12-03 lastmod: 2011-03-11 08:56:43 metadata_visibility: show title: Artificial neural networks as models of stimulus control ispublished: pub subjects: bio-etho subjects: comp-neuro-sci subjects: comp-sci-neural-nets subjects: bio-ani-behav full_text_status: public keywords: neural networks, animal behavior, generalization abstract: We evaluate the ability of artificial neural network models (multi-layer perceptrons) to predict stimulus-­response relationships. A variety of empirical results are considered, such as generalization, peak-shift (supernormality) and stimulus intensity effects. The networks were trained on the same tasks as the animals in the considered experiments. The subsequent generalization tests on the networks showed that the model replicates correctly the empirical results. It is concluded that these models are valuable tools in the study of animal behaviour. date: 1998 date_type: published publication: Animal Behaviour volume: 56 pagerange: 1383-1389 refereed: TRUE citation: Ghirlanda, Stefano and Enquist, Magnus (1998) Artificial neural networks as models of stimulus control. [Journal (Paginated)] document_url: http://cogprints.org/5271/1/ghirlanda_enquist1998.pdf