Investigation of neural networks for function approximation
In this work, some ubiquitous neural networks are applied to model the landscape of a
known problem function approximation. The performance of the various neural networks is …
known problem function approximation. The performance of the various neural networks is …
Improved NN-PID control of MIMO systems with PSO-based initialisation of weights
T Varshney, S Sheel - International Journal of Automation …, 2014 - inderscienceonline.com
To train the neural networks (NNs) standard back propagation (BP) algorithm and its
variations are widely used where initial weights are generated as random in nature. The …
variations are widely used where initial weights are generated as random in nature. The …
A dpso-based nn-pid controller for mimo systems
T Varshney, R Varshney, N Singh - Ambient Communications and …, 2018 - Springer
The neural networks are generally trained using the standard back propagation (BP)
algorithm and its variants. In the BP algorithm, the initial weights are generated randomly …
algorithm and its variants. In the BP algorithm, the initial weights are generated randomly …
[PDF][PDF] Function approximation of seawater density using genetic algorithm
Function Approximation is a popular engineering method used in system identification or
equation optimization. Artificial Intelligence (AI) techniques have been used extensively to …
equation optimization. Artificial Intelligence (AI) techniques have been used extensively to …
A Morlet wavelet neural network-based online identification and control of coupled MIMO systems
T Varshney, S Sheel - International Journal of Automation …, 2012 - inderscienceonline.com
A new approach has been developed for the control of a coupled, non-linear MIMO system.
A quasi-diagonal wavelet neural network (QDWNN)-based online identification and control …
A quasi-diagonal wavelet neural network (QDWNN)-based online identification and control …
[PDF][PDF] Using Artificial Neural Network Based Algorithm for Data Analysis of Fluorescence Lifetime Imaging
H Mao - 2014 - scholarworks.calstate.edu
Motivations of FLIM data analysis come from its unique diagnostic information and great
potential clinical role. However the important characteristic of FLIM data processing is the …
potential clinical role. However the important characteristic of FLIM data processing is the …