Redes de hopfield : modelando la memoria

"In 1982, John Hopfield proposes a model for the construction of artificial neural networks with the ability to store "memories" (network states) and recover them form fragments of their content. The collective behavior of the neurons defines a dynamical system in which the network state converges to one of the stored memories. The system's convergence can be considered as the minimization of an energy function. The algorithm has a close relationship with the minimum cut problem, and can also be applied to image processing. Lately, some modifications of the model have been implemented in memory related studies. The structure of the net resembles that of the hippocampus and captures some of the fundamental processes occurring in it".-- Tomado del Formato de Documento de Grado.

• Autores: Navas Zuloaga, María Gabriela
• Tipo de recurso: Trabajo de grado de pregrado
• Fecha de publicación: 2017
• Institución: Universidad de los Andes
• Repositorio: Séneca: repositorio Uniandes
• Idioma: spa
• OAI Identifier: oai:repositorio.uniandes.edu.co:1992/61350
• Acceso en línea: http://hdl.handle.net/1992/61350
• Palabra clave: Inteligencia artificial; Redes neurales (Computadores); Redes neurales (Neurobiología)
• Rights: openAccess
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/