M
Mahdi Aliyari Shoorehdeli
Researcher at K.N.Toosi University of Technology
Publications - 169
Citations - 2173
Mahdi Aliyari Shoorehdeli is an academic researcher from K.N.Toosi University of Technology. The author has contributed to research in topics: Fuzzy control system & Control theory. The author has an hindex of 20, co-authored 157 publications receiving 1812 citations. Previous affiliations of Mahdi Aliyari Shoorehdeli include Islamic Azad University, Science and Research Branch, Tehran & Islamic Azad University.
Papers
More filters
Proceedings ArticleDOI
Fault tolerant synchronization of chaotic heavy symmetric gyroscope systems via Gaussian RBF Neural Network Based on Sliding Mode Control
TL;DR: Numerical simulation results demonstrate the validity and feasibility of the proposed method to fault tolerant synchronization of chaotic gyroscope systems via Gaussian RBF neural network based on sliding mode control.
Proceedings ArticleDOI
Face detection based on dimension reduction using probabilistic neural network and Genetic Algorithm
TL;DR: This work argues that feature selection is an important issue in face and non-face classification and proposes a method to select a subset of features from the low-dimensional representation by removing certain eigenvectors that do not seem to encode important information about face.
Journal ArticleDOI
Application of constrained learning in making deep networks more transparent, regularized, and biologically plausible
TL;DR: It is demonstrated that not only does the proposed model have advantages of the previously proposed models potentially, but also it can be used as a technique for regularization of neural network weights and faster convergence.
Journal ArticleDOI
Modified projective synchronization of unknown chaotic dissipative gyroscope systems via Gaussian radial basis adaptive variable structure control
TL;DR: In this article, the modified projective synchronization method for unknown chaotic dissipative gyroscope systems via Gaussian radial basis adaptive variable structure control was proposed for secure communication in the presence of chaotic signals.
Posted Content
Between-Domain Instance Transition Via the Process of Gibbs Sampling in RBM.
TL;DR: This paper shows that the proposed method for Transfer Learning based on Gibbs Sampling can successfully enhance target classification by a considerable ratio and has the advantage over common DA methods that it needs no target data during the process of training of models.