adfa, p. 1, 2011. © Springer-Verlag Berlin Heidelberg 2011 A NEW OPTIMIZED CUCKOO SEARCH RECURRENT NEURAL NETWORK (CSRNN) ALGORITHM Nazri Mohd. Nawi 1 , Abdullah 1 , M. Z. Rehman 1 1 Software and Multimedia Centre, Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia (UTHM), P.O. Box 101, 86400 Parit Raja, BatuPahat, Johor DarulTakzim, Malaysia. nazri@uthm.edu.my, hi100010@siswa.uthm.edu.my, zrehman862060@gmail.com Abstract. Selecting the optimal topology of neural network for a particular ap- plication is a difficult task. In case of recurrent neural networks (RNN), most methods only introduce topologies in which their neurons are fully connected. However, recurrent neural network training algorithm has some drawbacks such as getting stuck in local minima, slow speed of convergence and network stag- nancy. This paper propose an improved recurrent neural network trained with Cuckoo Search (CS) algorithm to achieve fast convergence and high accuracy. The performance of the proposed Cuckoo Search Recurrent Neural Network (CSRNN) algorithm is compared with Artificial Bee Colony (ABC) and similar hybrid variants. The simulation results show that the proposed CSRNN algorithm performs better than other algorithms used in this study in terms of convergence rate and accuracy. Keywords: recurrent neural network, local minima, artificial bee colony, cuckoo search algorithm, hybrid neural networks, swarm optimization 1 Introduction The current advances in the working principles of Artificial Neural Networks (ANN) have paved way to classify, predict and forecast on nonlinear systems and huge datasets with high accuracy [1-5]. This makes ANN very attractive and considered superior to the classical modeling and control techniques. Among several possible network archi- tectures, the feed forward and recurrent neural networks (RNN) are most commonly used [6]. In a feed forward neural network the signals are transmitted only in one direc- tion, starting from the input layer, consequently through the hidden layers to the output layer. A recurrent neural network (RNN) has local feedback connections to some of the previous layers. It is different from feed forward network architecture in the sense that there is at least one feedback loop.