Period-Doublings to Chaos in a Simple Neural Network: An Analytical Proof
نویسنده
چکیده
The-dynamics of discrete-time neural networks with the sigmoid function as l}~uron activation function can be extraordinarily complex, as some authors have displayed in numerical simulations. Here we consider a simple neural network of only two neurons, one excitatory and the other inhibitory, with no external inputs and no time delay as a parameterized family of two-dimensional maps, and give an analytical proof for the existence of period-doublings to chaos and strange at tractors in the network.
منابع مشابه
Analysis and Diagnosis of Partial Discharge of Power Capacitors Using Extension Neural Network Algorithm and Synchronous Detection Based Chaos Theory
Power capacitors are important equipment of the power systems that are being operated in high voltage levels at high temperatures for long periods. As time goes on, their insulation fracture rate increases, and partial discharge is the most important cause of their fracture. Therefore, fast and accurate methods have great importance to accurately diagnosis the partial discharge. Conventional me...
متن کاملAN IMPROVED CONTROLLED CHAOTIC NEURAL NETWORK FOR PATTERN RECOGNITION
A sigmoid function is necessary for creation a chaotic neural network (CNN). In this paper, a new function for CNN is proposed that it can increase the speed of convergence. In the proposed method, we use a novel signal for controlling chaos. Both the theory analysis and computer simulation results show that the performance of CNN can be improved remarkably by using our method. By means of this...
متن کاملLarge amplitude vibration prediction of rectangular plates by an optimal artificial neural network (ANN)
In this paper, nonlinear equations of motion for laminated composite rectangular plates based on the first order shear deformation theory were derived. Using a perturbation method, the nonlinear equation of motion was solved and analytical relations were obtained for natural and nonlinear frequencies. After proving the validity of the obtained analytical relations, as an alternative and simple ...
متن کاملChaotic Test and Non-Linearity of Abnormal Stock Returns: Selecting an Optimal Chaos Model in Explaining Abnormal Stock Returns around the Release Date of Annual Financial Statements
For many investors, it is important to predict the future trend of abnormal stock returns. Thus, in this research, the abnormal stock returns of the listed companies in Tehran Stock Exchange were tested since 2008- 2017 using three hypotheses. The first and second hypotheses examined the non-linearity and non-randomness of the abnormal stock returns ′ trend around the release date of annual fin...
متن کاملAnalytical Prediction of the Two First Period-Doublings in a Three-Dimensional System
Analytical study of the two first period-doubling bifurcations in a three-dimensional system is reported. The multiple scales method is first applied to construct a higher-order approximation of the periodic orbit following Hopf bifurcation. The stability analysis of this periodic orbit is then performed in terms of Floquet theory to derive the critical parameter values corresponding to the fir...
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:
- Complex Systems
دوره 5 شماره
صفحات -
تاریخ انتشار 1991