Chaotic Dynamical Behavior of Recurrent Neural Network
نویسنده
چکیده
On account of their role played in the fundamental biological rhythms and by considering their potential use in information processing, the dynamical properties of an artificial neural network are particularly interesting to investigate. In order to reduce the degree of complexity of this work, we have considered in this paper a fully connected neural network of two discrete neurons. We have proceeded to a qualitative and quantitative study of their state evolution by means of numerical simulation. The first aim was to find the possible equilibrium states. Other authors have already shown that some oscillating state can occur. So, the second aim was to analyze the dynamical properties of each of them. We have computed the value of the Lyapunov’s exponents and the fractal dimension. The sensitivity of the dynamical characteristics to parameters such as the weights of the connections and the shape of the activation function has been studied.
منابع مشابه
بهبود بازشناسی مقاوم الگو در شبکه های عصبی بازگشتی جاذب از طریق به کارگیری دینامیک های آشوب گونه
In this paper, two kinds of chaotic neural networks are proposed to evaluate the efficiency of chaotic dynamics in robust pattern recognition. The First model is designed based on natural selection theory. In this model, attractor recurrent neural network, intelligently, guides the evaluation of chaotic nodes in order to obtain the best solution. In the second model, a different structure of ch...
متن کاملA recurrent neural network without chaos
We introduce an exceptionally simple gated recurrent neural network (RNN) that achieves performance comparable to well-known gated architectures, such as LSTMs and GRUs, on the word-level language modeling task. We prove that our model has simple, predicable and non-chaotic dynamics. This stands in stark contrast to more standard gated architectures, whose underlying dynamical systems exhibit c...
متن کاملSolving Linear Semi-Infinite Programming Problems Using Recurrent Neural Networks
Linear semi-infinite programming problem is an important class of optimization problems which deals with infinite constraints. In this paper, to solve this problem, we combine a discretization method and a neural network method. By a simple discretization of the infinite constraints,we convert the linear semi-infinite programming problem into linear programming problem. Then, we use...
متن کاملA Recurrent Neural Network for Solving Strictly Convex Quadratic Programming Problems
In this paper we present an improved neural network to solve strictly convex quadratic programming(QP) problem. The proposed model is derived based on a piecewise equation correspond to optimality condition of convex (QP) problem and has a lower structure complexity respect to the other existing neural network model for solving such problems. In theoretical aspect, stability and global converge...
متن کاملLearning Chaotic Dynamics using Tensor Recurrent Neural Networks
We present Tensor-RNN, a novel RNN architecture for multivariate forecasting in chaotic dynamical systems. Our proposed architecture captures highly nonlinear dynamic behavior by using high-order Markov states and transition functions. Furthermore, we decompose the highdimensional structure of the model using tensortrain networks to reduce the number of parameters while preserving the model per...
متن کاملOn the Dynamics of Small Continuous-Time Recurrent Neural Networks
Dynamical neural networks are being increasingly employed in a variety of different contexts, including as simple model nervous systems for autonomous agents. For this reason, there is a growing need for a comprehensive understanding of their dynamical properties. Using a combination of elementary analysis and numerical experiments, this paper begins a systematic study of the dynamics of contin...
متن کامل