Learning to recognize or predict sequences using long-term context has many applications. However, practical and theoretical problems are found in training recurrent neural networ...
Practical Recurrent Learning (PRL) has been proposed as a simple learning algorithm for recurrent neural networks[1][2]. This algorithm enables learning with practical order O(n2 )...
Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
Abstract. Compared to normal learning algorithms, for example backpropagation, the optimal bounded ellipsoid (OBE) algorithm has some better properties, such as faster convergence,...
— We investigate the use of Particle Swarm Optimization (PSO), and compare with Genetic Algorithms (GA), for a particular robot behavior-learning task: the training of an animat ...