Hunter R, Cobb SR & Graham B (2008) Improving Associative Memory in a Network of Spiking Neurons. In: Kurkova V, Neruda R & Koutnik J (eds.) Artificial Neural Networks - ICANN 2008: 18th International Conference, Prague, Czech Republic, September 3-6, 2008, Proceedings, Part II. Lecture Notes in Computer Science, 5164. 18th International Conference on Artificial Neural Networks –ICANN 2008, Prague, Czech Republic, 03.09.2008-06.09.2008. Berlin, Germany: Springer-Verlag, pp. 636-645. http://www.springerlink.com/content/b98q662816538526/; https://doi.org/10.1007/978-3-540-87559-8_66
Associative neural network models are a commonly used methodology when investigating the theory of associative memory in the brain. Comparisons between the mammalian hippocampus and neural network models of associative memory have been investigated. Biologically based networks are complex systems built of neurons with a variety of properties. Here we compare and contrast associative memory function in a network of biologically-based spiking neurons with previously published results for a simple artificial neural network model. We investigate biologically plausible implementations of methods for improving recall under biologically realistic conditions, such as a sparsely connected network.
Associative memory; Mammalian hippocampus; Neural networks; Pattern recall; Inhibition