Global parameter identification in systems with a sigmoidal activation function
نویسندگان
چکیده
Parameter identification in a 2-node network with sigmoidal activation functions is considered. Given the nonlinearity in the weights, standard estimation algorithms based on linear parametrization are inadequate tools for studying global parameter convergence. In this paper, we provide an alternative approach for studying parameter identification in the presence of sigmoidal parametrization. Conditions under which a simple back propagation algorithm can lead to global convergence are considered.
منابع مشابه
Non-linear Fractional-Order Chaotic Systems Identification with Approximated Fractional-Order Derivative based on a Hybrid Particle Swarm Optimization-Genetic Algorithm Method
Although many mathematicians have searched on the fractional calculus since many years ago, but its application in engineering, especially in modeling and control, does not have many antecedents. Since there are much freedom in choosing the order of differentiator and integrator in fractional calculus, it is possible to model the physical systems accurately. This paper deals with time-domain id...
متن کاملChemical Capture of CO2 by Glycine Salt Solution
The role of carbon dioxide in global warming is one of the contemporary environmental issues and it is, therefore, necessary to have available technology to capture the released CO2 into the atmosphere. Amino acids have the same amine functionality as alkanolamines with similar behavior towards CO2 absorption. The solubility of carbon dioxide in potassium glycinate (KG) solutions with different...
متن کاملA Three-Coefficient Model with Global Optimization for Heavy End Characterization of Gas Condensate PVT Data
Characterization of heavy end, as plus fraction, is among the most crucial steps in predicting phase behavior of a hydrocarbon fluid system. Proper selection of single carbon number (SCN) distribution function is essential for heavy end characterization. The SCN distribution function is subject to fluid nature. The exponential distribution function has been and is widely applied to gas condensa...
متن کاملRecurrent Neural Networks: Some Systems-Theoretic Aspects∗
This paper provides an exposition of some recent research regarding system-theoretic aspects of continuous-time recurrent (dynamic) neural networks with sigmoidal activation functions. The class of systems is introduced and discussed, and a result is cited regarding their universal approximation properties. Known characterizations of controllability, observability, and parameter identifiability...
متن کاملVerification of an Evolutionary-based Wavelet Neural Network Model for Nonlinear Function Approximation
Nonlinear function approximation is one of the most important tasks in system analysis and identification. Several models have been presented to achieve an accurate approximation on nonlinear mathematics functions. However, the majority of the models are specific to certain problems and systems. In this paper, an evolutionary-based wavelet neural network model is proposed for structure definiti...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2000