Title :
Transient responses in dynamical neural models
Author :
Stiber, Michael ; Segundo, J.P.
Author_Institution :
Dept. of Comput. Sci., Hong Kong Univ. of Sci. & Technol., Hong Kong
Abstract :
The authors consider the input/output behavior of a realistic dynamical neural model in comparison to those typically used in artificial neural networks. They have found that such models duplicate well those behaviors seen in living neurons, displaying a range of behaviors commonly seen in a wide variety of nonlinear dynamical systems. This is not captured well by weighted sum/monotonic transfer function models. An example of the consequences of nonlinear dynamics in neural responses is presented for monotonically changing input transients
Keywords :
neural nets; neurophysiology; nonlinear dynamical systems; physiological models; transient response; artificial neural networks; dynamical neural models; input transients; input/output behavior; living neurons; neural responses; nonlinear dynamical systems; nonlinear dynamics; transient responses; weighted sum/monotonic transfer function models; Biological neural networks; Biological system modeling; Computer networks; Feedforward neural networks; Nervous system; Neural networks; Neurons; Nonlinear dynamical systems; Switches; Transfer functions;
Conference_Titel :
Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on
Print_ISBN :
0-7803-1865-X
DOI :
10.1109/SIPNN.1994.344925
