R
Ralph Neuneier
Researcher at Siemens
Publications - 44
Citations - 1096
Ralph Neuneier is an academic researcher from Siemens. The author has contributed to research in topics: Artificial neural network & Recurrent neural network. The author has an hindex of 15, co-authored 44 publications receiving 1033 citations.
Papers
More filters
Journal ArticleDOI
Risk Sensitive Reinforcement Learning
Ralph Neuneier,Oliver Mihatsch +1 more
TL;DR: This risk-sensitive reinforcement learning algorithm is based on a very different philosophy and reflects important properties of the classical exponential utility framework, but avoids its serious drawbacks for learning.
Proceedings Article
Training Neural Networks with Deficient Data
TL;DR: The general solution requires a weighted integration over the unknown or uncertain input although computationally cheaper closed-form solutions can be found for certain Gaussian Basis Function networks.
Book ChapterDOI
How to Train Neural Networks
TL;DR: The Observer - Observation Dilemma is solved by forcing the network to construct smooth approximation functions, and some pruning algorithms to optimize the network architecture are proposed.
Proceedings Article
Efficient Methods for Dealing with Missing Data in Supervised Learning
TL;DR: This work presents efficient algorithms for dealing with the problem of missing inputs (incomplete feature vectors) during training and recall based on the approximation of the input data distribution using Parzen windows.
Proceedings Article
Optimal Asset Allocation using Adaptive Dynamic Programming
TL;DR: Asset allocation is formalized as a Markovian Decision Problem which can be optimized by applying dynamic programming or reinforcement learning based algorithms and is shown to be equivalent to a policy computed by dynamic programming.