@article{(Open Science Index):https://publications.waset.org/pdf/12598, title = {Evolutionary Training of Hybrid Systems of Recurrent Neural Networks and Hidden Markov Models}, author = {Rohitash Chandra and Christian W. Omlin}, country = {}, institution = {}, abstract = {We present a hybrid architecture of recurrent neural networks (RNNs) inspired by hidden Markov models (HMMs). We train the hybrid architecture using genetic algorithms to learn and represent dynamical systems. We train the hybrid architecture on a set of deterministic finite-state automata strings and observe the generalization performance of the hybrid architecture when presented with a new set of strings which were not present in the training data set. In this way, we show that the hybrid system of HMM and RNN can learn and represent deterministic finite-state automata. We ran experiments with different sets of population sizes in the genetic algorithm; we also ran experiments to find out which weight initializations were best for training the hybrid architecture. The results show that the hybrid architecture of recurrent neural networks inspired by hidden Markov models can train and represent dynamical systems. The best training and generalization performance is achieved when the hybrid architecture is initialized with random real weight values of range -15 to 15.}, journal = {International Journal of Computer and Information Engineering}, volume = {2}, number = {3}, year = {2008}, pages = {817 - 822}, ee = {https://publications.waset.org/pdf/12598}, url = {https://publications.waset.org/vol/15}, bibsource = {https://publications.waset.org/}, issn = {eISSN: 1307-6892}, publisher = {World Academy of Science, Engineering and Technology}, index = {Open Science Index 15, 2008}, }