We propose a novel, high-level model of human learning and cognition, based on association forming. The model configures any input data stream featuring a high incidence of repetition into an association network whose node clusters represent data 'concepts'. It relies on the hypothesis that, irrespective of the high parallelism of the neural structures involved in cognitive processes taking place in the brain cortex, the channel through which the information is conveyed from the real world environment to its final location (in whatever form of neural structure) can transmit only one data item per time unit. Several experiments are performed on the ability of the resulting system to reconstruct a given underlying 'world graph' of concepts and to form and eventually maintain a stable, long term core of memory that we call 'semantic' memory. The existence of discontinuous, first order phase transitions in the dynamics of the system is supported with experiments. Results on clustering and association are shown as well. © Springer-Verlag Berlin Meldelberg 2005.
Documento: | Artículo |
Título: | Modelling human intelligence: A learning mechanism |
Autor: | Segura, E.C.; Whitty, R. |
Ciudad: | Monterrey |
Filiación: | Departamento de Computacion, Facultad de Ciencias Exactas y Naturales, Ciudad Universitaria, Pabellon I, (1428) Buenos Aires, Argentina School of Business, Computing and Information Management, London South Bank University, London SE1A 0AA, United Kingdom |
Palabras clave: | Association network; Graph; Learning; Memory; Stability; Cognitive systems; Graph theory; Human computer interaction; Learning systems; Neural networks; Semantics; Stability; Association network; Graph; Learning; Memory; Artificial intelligence |
Año: | 2005 |
Volumen: | 3789 LNAI |
Página de inicio: | 1 |
Página de fin: | 10 |
DOI: | http://dx.doi.org/10.1007/11579427_1 |
Título revista: | 4th Mexican International Conference on Artificial Intelligence, MICAI 2005 |
Título revista abreviado: | Lect. Notes Comput. Sci. |
ISSN: | 03029743 |
Registro: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_03029743_v3789LNAI_n_p1_Segura |