EEL6935 Information Theoretical Learning Project 1 Time Delay Neural Network with MEE Criteria
نویسندگان
چکیده
The sun spot time series is a random series generated with a complicated nonlinear system. Time delay neural networks (TDNN) are typical nonlinear systems that could be used to perform time series prediction. In this project, we applied the TDNN trained with both MSE and MEE criteria to predict the time series. Both criteria showed the effectiveness of the nonlinear systems. Furthermore, the TDNN system trained with MEE criteria performs even better that the conventional MSE criteria in one-step prediction. By this result, we showed the advantage of utilizing the information theory to minimizing the error entropy over the MSE criteria.
منابع مشابه
Evaluating project’s completion time with Q-learning
Nowadays project management is a key component in introductory operations management. The educators and the researchers in these areas advocate representing a project as a network and applying the solution approaches for network models to them to assist project managers to monitor their completion. In this paper, we evaluated project’s completion time utilizing the Q-learning algorithm. So the ...
متن کاملGDOP Classification and Approximation by Implementation of Time Delay Neural Network Method for Low-Cost GPS Receivers
Geometric Dilution of Precision (GDOP) is a coefficient for constellations of Global Positioning System (GPS) satellites. These satellites are organized geometrically. Traditionally, GPS GDOP computation is based on the inversion matrix with complicated measurement equations. A new strategy for calculation of GPS GDOP is construction of time series problem; it employs machine learning and artif...
متن کاملSynergies between Intrinsic and Synaptic Plasticity Based on Information Theoretic Learning
In experimental and theoretical neuroscience, synaptic plasticity has dominated the area of neural plasticity for a very long time. Recently, neuronal intrinsic plasticity (IP) has become a hot topic in this area. IP is sometimes thought to be an information-maximization mechanism. However, it is still unclear how IP affects the performance of artificial neural networks in supervised learning a...
متن کاملJoint influence of leakage delays and proportional delays on almost periodic solutions for FCNNs
This paper deals with fuzzy cellular neural networks (FCNNs) with leakage delays and proportional delays. Applying the differential inequality strategy, fixed point theorem and almost periodic function principle, some sufficient criteria which ensure the existence and global attractivity of a unique almost periodic solution for fuzzy cellular neuralnetworks with leakage delays and p...
متن کاملEvaluating project’s completion time with Q-learning
Nowadays project management is a key component in introductory operations management. The educators and the researchers in these areas advocate representing a project as a network and applying the solution approaches for network models to them to assist project managers to monitor their completion. In this paper, we evaluated project’s completion time utilizing the Q-learning algorithm. So the ...
متن کامل