Complex RTRL Neural Networks Fast Kalman Training

This paper presents an extended fast Kalman filter training procedure for complex RTRL neural networks. Fast Kalman training methods use the framework for extended Kalman filtering techniques which proved to be efficient but quite computationally demanding particularly when a large number of states is involved. In standard Kalman filtering algorithms the number of multiplications is proportional to the square of the number of states while in Fast Kalman algorithms that number is proportional to the number of states. Fast Kalman/extended Kalman filter complex RTRL training algorithms inherit the convergence capabilities of the standard extended Kalman filter techniques and are adequate for complex RTRL neural networks training involving a large number of states. Simulations were carried out which indicate the success of the method.