M. Forcada and R. Carrasco. Finite-state computation in analog neural networks: Steps towards biologically plausible models? In S. Wermter, J. Austin, and D. Willshaw, editors, Emergent Neural Computational Architectures based on Neuroscience (this volume). Springer-Verlag, Heidelberg, Germany, 2001.  Home/Search   Document Details and Download   Summary   Related Articles

....intelligent computer systems typically as arti cial neural networks. However, in most systems the computational elements are still a gross simpli cation of biological neurons. There is too little biological plausibility or indication of how the brain constrains can incorporated in a better way [66, 12, 25]. Nevertheless, Hanson et al. 2001) 35] in this volume outlines that arti cial neural network such as recurrent ones can perform emergent behaviour close to human cognitive performance. These networks are able to produces an abstract structure that is situation sensitive, hierarchical and ....

....characteristics of the model its performance is examined using plausible values of system variables. The outcomes display that robust memory traces can be produced if one assumes there is an episodic memory capacity of 75,000 events made up of 300,000 bindings. Forcada and Carrasco (2001) [25] argue that, although a nite state machine could be modelled by any discrete time recurrent neural network (DTRNN) with discrete time processing elements, biological networks perform in continuous time and so methods for synchronisation and memory should be postulated. It ought to be possible to ....

[Article contains additional citation context not shown here]

M. Forcada and R. Carrasco. Finite-state computation in analog neural networks: Steps towards biologically plausible models? In S. Wermter, J. Austin, and D. Willshaw, editors, Emergent Neural Computational Architectures based on Neuroscience (this volume). Springer-Verlag, Heidelberg, Germany, 2001.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC