Categorisation through evidence accumulation in an active vision system
| Autor: | Tomassino Ferrauto, Stefano Nolfi, Marco Mirolli |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
active vision
Process (engineering) Computer science media_common.quotation_subject 050105 experimental psychology 03 medical and health sciences 0302 clinical medicine Artificial Intelligence Human–computer interaction Perception Genetic algorithm 0501 psychology and cognitive sciences Active vision media_common Active vision system Artificial neural network business.industry 05 social sciences neural networks Artificial vision system Human-Computer Interaction Action (philosophy) categorisation Artificial intelligence business 030217 neurology & neurosurgery Software |
| Zdroj: | Connection science 22 (2010): 331–354. doi:10.1080/09540091.2010.505976 info:cnr-pdr/source/autori:Mirolli M., Ferrauto T., Nolfi S./titolo:Categorisation through Evidence Accumulation in an Active Vision System/doi:10.1080%2F09540091.2010.505976/rivista:Connection science (Print)/anno:2010/pagina_da:331/pagina_a:354/intervallo_pagine:331–354/volume:22 |
| ISSN: | 1360-0494 0954-0091 |
| DOI: | 10.1080/09540091.2010.505976 |
| Popis: | In this paper, we present an artificial vision system that is trained with a genetic algorithm for categorising five different kinds of images (letters) of different sizes. The system, which has a limited field of view, can move its eye so as to explore the images visually. The analysis of the system at the end of the training process indicates that correct categorisation is achieved by (1) exploiting sensory-motor coordination so as to experience stimuli that facilitate discrimination, and (2) integrating perceptual and/or motor information over time through a process of accumulation of partially conflicting evidence. We discuss our results with respect to the possible different strategies for categorisation and to the possible roles that action can play in perception. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |