Interpretação de Imagens como Tarefa Cognitiva: uma Abordagem Inicial com Redes Neurais de Aprendizagem Profunda
Resumo
O presente trabalho aborda a funcionalidade de interpretar imagens como uma tarefa cognitiva em agentes. Para verificar alguns dos limites das abordagens consideradas mais efetivas foram efetuados experimentos com redes convolucionais. A principal contribuição, a partir dos resultados, é a constatação e explicitação de possíveis caminhos para elaborar uma arquitetura cognitiva que, embora utilize aprendizagem profunda para aquisição de entradas, o faça sob um arcabouço cognitivo.Referências
Biederman, I. (1987). Recognition-by-components: a theory of human image understanding. Psychological review, 94(2):115.
Fodor, J. A. (1983). The modularity of mind: An essay on faculty psychology. MIT press.
Guarino, N. (1995). Formal ontology, conceptual analysis and knowledge representation. International journal of human-computer studies, 43(5-6):625–640.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.
Ikeuchi, K. (2014). Computer vision: A reference guide. Springer Publishing Company, Incorporated.
Lampert, C. H., Nickisch, H., and Harmeling, S. (2014). Attribute-based classification for zero-shot visual object categorization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(3):453–465.
Marr, D. and Vision, A. (1982). A computational investigation into the human representation and processing of visual information. WH San Francisco: Freeman and Company, 1(2).
Noy, N. F., McGuinness, D. L., et al. (2001). Ontology development 101: A guide to creating your first ontology.
Prinz, J. (2012). The conscious brain. Oxford University Press.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Studer, R., Benjamins, V. R., and Fensel, D. (1998). Knowledge engineering: principles and methods. Data & knowledge engineering, 25(1-2):161–197.
Fodor, J. A. (1983). The modularity of mind: An essay on faculty psychology. MIT press.
Guarino, N. (1995). Formal ontology, conceptual analysis and knowledge representation. International journal of human-computer studies, 43(5-6):625–640.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778.
Ikeuchi, K. (2014). Computer vision: A reference guide. Springer Publishing Company, Incorporated.
Lampert, C. H., Nickisch, H., and Harmeling, S. (2014). Attribute-based classification for zero-shot visual object categorization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(3):453–465.
Marr, D. and Vision, A. (1982). A computational investigation into the human representation and processing of visual information. WH San Francisco: Freeman and Company, 1(2).
Noy, N. F., McGuinness, D. L., et al. (2001). Ontology development 101: A guide to creating your first ontology.
Prinz, J. (2012). The conscious brain. Oxford University Press.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Studer, R., Benjamins, V. R., and Fensel, D. (1998). Knowledge engineering: principles and methods. Data & knowledge engineering, 25(1-2):161–197.
Publicado
02/05/2018
Como Citar
CARNEIRO, Cleverson; BELESKI, Nicolas Mansur; LUGO, Gustavo Giménez.
Interpretação de Imagens como Tarefa Cognitiva: uma Abordagem Inicial com Redes Neurais de Aprendizagem Profunda. In: WORKSHOP-ESCOLA DE SISTEMAS DE AGENTES, SEUS AMBIENTES E APLICAÇÕES (WESAAC), 12. , 2018, Fortaleza/CE.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2018
.
p. 265-268.
ISSN 2326-5434.
DOI: https://doi.org/10.5753/wesaac.2018.33277.
