11 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 10 / 11
Yayın A new robust stability criterion for dynamical neural networks with multiple time delays(Elsevier Science BV, 2013-01-01) Faydasıçok, Özlem; Arik, SabriThis paper investigates the problem of the existence, uniqueness and global asymptotic stability of the equilibrium point for the class of neural networks with multiple time delays and parameter uncertainties. Under the assumption that the activation functions are globally Lipschitz continuous, we derive a new criterion for the robust stability of a class of delayed neural networks by utilizing the Lyapunov stability theorems and the Homomorphic mapping theorem. Different from those previously published conditions in the recent literature, the robust stability result presented in this paper not only establishes a time-independent relationship between the network parameters of the neural network, but also takes into account the number the neurons of the designed neural system. Some illustrative numerical examples are also given to make a detailed comparison between our result and the previously published corresponding results. This comparison proves that our result is new and can be considered an alternative condition to those of the previously reported robust stability results.Yayın Dynamical analysis of uncertain neural networks with multiple time delays(Taylor & Francis Ltd, 2016-02-17) Arık, SabriThis paper investigates the robust stability problem for dynamical neural networks in the presence of time delays and norm-bounded parameter uncertainties with respect to the class of non-decreasing, non-linear activation functions. By employing the Lyapunov stability and homeomorphism mapping theorems together, a new delay-independent sufficient condition is obtained for the existence, uniqueness and global asymptotic stability of the equilibrium point for the delayed uncertain neural networks. The condition obtained for robust stability establishes a matrix-norm relationship between the network parameters of the neural system, which can be easily verified by using properties of the class of the positive definite matrices. Some constructive numerical examples are presented to show the applicability of the obtained result and its advantages over the previously published corresponding literature results.Yayın Neural network steering control algorithm for autonomous ground vehicles having signal time delay(SAGE Publications Ltd, 2024-03) Dinçmen, ErkinAn adaptive neural network–based steering control algorithm is proposed for yaw rate tracking of autonomous ground vehicles with in-vehicle signal time delay. The control system consists of two neural networks: the observer neural network and the controller neural network. The observer neural network adapts itself to the system dynamics during the training phase. Once trained, the observer neural network cooperates with the controller neural network, which constantly adapts itself during the control task. In this way, an adaptive and intelligent control structure is proposed. Through simulation studies, it has been shown that while a proportional-integral-derivative type steering controller fails to perform its control task in case of steering signal delay, the proposed control algorithm manages to adapt itself according to the control problem and achieves reference yaw rate tracking. The robustness of the control algorithm according to the signal delay magnitude has been demonstrated by simulation studies. A rigorous Lyapunov stability analysis of the control algorithm is also presented.Yayın CNN-Based deep learning architecture for electromagnetic imaging of rough surface profiles(IEEE, 2022-10) Aydın, İzde; Budak, Güven; Sefer, Ahmet; Yapar, AliA convolutional neural network (CNN) based deep learning (DL) technique for electromagnetic imaging of rough surfaces separating two dielectric media is presented. The direct scattering problem is formulated through the conventional integral equations and the synthetic scattered field data is produced by a fast numerical solution technique which is based on Method of Moments (MoM). Two different special CNN architectures are designed and implemented for the solution of the inverse rough surface imaging problem wherein both random and deterministic rough surface profiles can be imaged. It is shown by a comprehensive numerical analysis that the proposed deep-learning (DL) inversion scheme is very effective and robust.Yayın End-effector trajectory control in a two-link flexible manipulator through reference joint angle values modification by neural networks(Sage Publications, 2006-02) Öke, Gülay; İstefanopulos, YorgoThe basic difficulty in the control of flexible link manipulators stems from the fact that the link deflections cannot be controlled directly. Since the number of control inputs, applied by the actuators, is less than the total number of variables to be controlled, control approaches aiming at the suppression of deflections and vibrations are generally insufficient. Another possible approach is to determine new joint trajectories to minimize the error of the end-effector in the operational space. In this paper, a neural network is designed to compute incremental changes for the reference values of the joint angles to achieve successful tip tracking in the operational space. Tip position errors in the x- and y-directions are utihzed as inputs to the neural network. The cost function, which is minimized in training the neural network, is also chosen as the sum of squares of the tip position error in both directions. Joint angle control is provided by a PD controller. Simulations are carried out to evaluate the performance of the neural-network-based trajectory tracking method, and the results are depicted in both joint and operational spaces.Yayın A novel similarity based unsupervised technique for training convolutional filters(IEEE, 2023-05-17) Erkoç, Tuğba; Eskil, Mustata TanerAchieving satisfactory results with Convolutional Neural Networks (CNNs) depends on how effectively the filters are trained. Conventionally, an appropriate number of filters is carefully selected, the filters are initialized with a proper initialization method and trained with backpropagation over several epochs. This training scheme requires a large labeled dataset, which is costly and time-consuming to obtain. In this study, we propose an unsupervised approach that extracts convolutional filters from a given dataset in a self-organized manner by processing the training set only once without using backpropagation training. The proposed method allows for the extraction of filters from a given dataset in the absence of labels. In contrast to previous studies, we no longer need to select the best number of filters and a suitable filter weight initialization scheme. Applying this method to the MNIST, EMNIST-Digits, Kuzushiji-MNIST, and Fashion-MNIST datasets yields high test performances of 99.19%, 99.39%, 95.03%, and 90.11%, respectively, without applying backpropagation training or using any preprocessed and augmented data.Yayın Robust stability analysis of a class of neural networks with discrete time delays(Pergamon-Elsevier Science Ltd, 2012-05) Faydasıçok, Özlem; Arik, SabriThis paper studies the existence, uniqueness and global asymptotic stability of the equilibrium point for the class of neural networks with discrete constant time delays under parameter uncertainties. The class of the neural network considered in this paper employs the activation functions which are assumed to be continuous and slope-bounded but not required to be bounded or differentiable. We conduct a stability analysis by exploiting the stability theory of Lyapunov functionals and the theory of Homomorphic mapping to derive some easily verifiable sufficient conditions for existence, uniqueness and global asymptotic stability of the equilibrium point. The conditions obtained mainly establish some time-independent relationships between the network parameters of the neural network. We make a detailed comparison between our results and the previously published corresponding results. This comparison proves that our results are new and improve and generalize the results derived in the past literature. We also give some illustrative numerical examples to show the effectiveness and applicability of our proposed stability results.Yayın A novel method to represent speech signals(Elsevier Science BV, 2005-01) Akdeniz, Rafet; Yarman, Bekir Sıddık BinboğaIn this work, speech signals are modeled by means of the so-called pre-defined "signature functions". The pre-defined signature functions are generated using the statistical properties of the speech signals. It has been exhibited that, with a few basic signature functions, any speech signal can be generated within a tolerable error.Yayın An improved robust stability result for uncertain neural networks with multiple time delays(Pergamon-Elsevier Science Ltd, 2014-06) Arik, SabriThis paper proposes a new alternative sufficient condition for the existence, uniqueness and global asymptotic stability of the equilibrium point for the class of delayed neural networks under the parameter uncertainties of the neural system. The existence and uniqueness of the equilibrium point is proved by using the Homomorphic mapping theorem. The asymptotic stability of the equilibrium point is established by employing the Lyapunov stability theorems. The obtained robust stability condition establishes a new relationship between the network parameters of the system. We compare our stability result with the previous corresponding robust stability results derived in the past literature. Some comparative numerical examples together with some simulation results are also given to show the applicability and advantages of our result.Yayın ANN activation function estimators for homomorphic encrypted inference(Institute of Electrical and Electronics Engineers Inc., 2025-06-13) Harb, Mhd Raja Abou; Çeliktaş, BarışHomomorphic Encryption (HE) enables secure computations on encrypted data, facilitating machine learning inference in sensitive environments such as healthcare and finance. However, efficiently handling non-linear activation functions, specifically Sigmoid and Tanh, remains a significant computational challenge for encrypted inference using Artificial Neural Networks (ANNs). This study introduces a lightweight, ANN-based estimator designed to accurately approximate activation functions under homomorphic encryption. Unlike traditional polynomial and piecewise linear approximations, the proposed ANN estimators achieve superior accuracy with lower computational overhead associated with bootstrapping or high-degree polynomial techniques. These estimators are trained on plaintext data and seamlessly integrated into encrypted inference pipelines, significantly outperforming conventional methods. Experimental evaluations demonstrate notable improvements, with ANN estimators enhancing accuracy by approximately 2% for Sigmoid and up to 73% for Tanh functions, improving F1-scores by approximately 2% for Sigmoid and up to 88% for Tanh, and markedly reducing Mean Square Error (MSE) by up to 96% compared to polynomial approximations. The ANN estimator achieves an accuracy of 97.70% and an AUC of 0.9997 when integrated into a CNN architecture on the MNIST dataset, and an accuracy of 85.25% with an AUC of 0.9459 on the UCI Heart Disease dataset during ciphertext inference. These results underscore the estimator’s practical effectiveness and computational feasibility, making it suitable for secure and efficient ANN inference in encrypted environments.
