Rprop - Description and Implementation Details

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition (2010, methodology): “After 300 epochs using the RPROP [19] batch-learning algorithm, we evaluated the normalized recognition performance for Caltech-101.”
Integration of Spectral Feature Extraction and Modeling for HMM-Based Speech Synthesis (2014, methodology): “For a large scale experiment, we reduced the computational cost in (3) by changing the optimization method from the NewtonRaphson method to the RPROP [23] method and using the distributed processing in the estimation of Q (c).”
Learning Motion Skills from Expert Demonstrations and Own Experience using Gaussian Process Regression (2010, background): “For this purpose, we maximize abest = argmax a µ(scurr, a)− σ(scurr, a) (6) through Rprop [11] gradient descent, which is faster than standard gradient descent and is less susceptible to end in local maxima.”
Neural Networks in R Using the Stuttgart Neural Network Simulator: RSNNS (2012, methodology): “This interface can be accessed by the low-level interface functions of RSNNS . neuralnet The package neuralnet (Fritsch et al. 2010) implements standard backpropagation and two types of resilient backpropagation (Riedmiller and Braun 1993; Riedmiller 1994).”
A segmental CRF approach to large vocabulary continuous speech recognition (2009, unknown): “Training is done by gradient descent using Rprop [19].”