This brief presents an efficient and scalable online learning algorithm for recurrent neural networks (RNNs). The approach is based on the real-time recurrent learning (RTRL) algor...
The method of conjugate gradients provides a very effective way to optimize large, deterministic systems by gradient descent. In its standard form, however, it is not amenable to ...
Recently, an optimization approach for fast visual tracking of articulated structures based on Stochastic Meta-Descent (SMD) [7] has been presented. SMD is a gradient descent with...
Matthieu Bray, Esther Koller-Meier, Nicol N. Schra...