Evolutionary Training of Hybrid Systems of Recurrent Neural Networks and Hidden Markov Models

Free registration required

Executive Summary

The authors present hybrid architecture of Recurrent Neural Networks (RNNs) inspired by Hidden Markov Models (HMMs). They train the hybrid architecture using genetic algorithms to learn and represent dynamical systems. They 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, they show that the hybrid system of HMM and RNN can learn and represent deterministic finite-state automata. They ran experiments with different sets of population sizes in the genetic algorithm; they also ran experiments to find out which weight initializations were best for training the hybrid architecture.

  • Format: PDF
  • Size: 483.1 KB