Improving the Rprop Learning Algorithm

By Christian Igel, Michael Hüsken. 2000

380 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Hyper-Parameter Optimization: A Review of Algorithms and Applications (2020, background): “It can be considered the development of Rprop (Igel and Hüsken, 2000) for mini-batch weight update.”
Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods (2007, methodology): “One significant barrier for applying the method (as well as other methods based on IRL) is that it needs to solve MDPs many times.”
An Introductory Review of Deep Learning for Prediction Models With Big Data (2020, methodology): “The resilient backpropagation algorithm (Rprop) is a modiﬁcation of the backpropagation algorithm that was originally introduced to speed up the basic backpropagation (Bprop) algorithm (Riedmiller and Braun, 1993).”
Simulations approaching data: cortical slow waves in inferred models of the whole hemisphere of mouse (2021, unknown): “Spatial maps of estimated parameters after 700 iterations of iRprop [24], that we further improved by setting priors for the expected spatial decay law of lateral connectivity.”
Empirical evaluation of the improved Rprop learning algorithms (2003, methodology): “In the next section, we describe the Rprop algorithm as proposed by Riedmiller and Braun [17, 18] and our modifications firstly suggested in [6].”
Optimization for problem classes-neural networks that learn to learn (2000, methodology): “The iRprop+-Algorithm (Igel and Hüsken 2000), an improved version of the Rprop-Algorithm (Riedmiller 1994), is employed to minimize the mean squared error e = 1 P ∑P p=1 (ŷp − yp) 2.”
Recurrent neural networks for time series classification (2003, methodology): “The learning algorithm iRprop [7,8] is an improved version of the well performing Rprop-algorithm [11,12], a gradient-based learning method with adaptive step size control.”