This paper presents FC networks that are instantaneously trained neural networks that allow rapid learning of non-binary data. These networks, which generalize the earlier CC netw...
Abstract. The performance of financial forecasting with neural networks dependents on the particular training set. We design mean-change-point test to divide the original dataset i...
Abstract. Experiments of neural network training procedure parallelization are conducted. Several styles of parallelization are described and compared, estimations of neural networ...
Abstract. In this paper we present a Reinforcement Learning (RL) approach with the capability to train neural adaptive controllers for complex control problems without expensive on...