Publica
Hier finden Sie wissenschaftliche Publikationen aus den FraunhoferInstituten. Bayesian Perceptron: Towards fully Bayesian Neural Networks
 Institute of Electrical and Electronics Engineers IEEE; IEEE Control Systems Society; Society for Industrial and Applied Mathematics SIAM, Philadelphia/Pa.: 59th IEEE Conference on Decision and Control, CDC 2020 : December 14th18th 2020, Virtuell, Jeju Island, Korea (South) Piscataway, NJ: IEEE, 2020 ISBN: 9781728174488 ISBN: 9781728174464 ISBN: 9781728174471 pp.31793186 
 Conference on Decision and Control (CDC) <59, 2020, Online> 

 English 
 Conference Paper 
 Fraunhofer IPA () 
 Bayesian network; Künstliche Intelligenz; maschinelles Lernen; neuronales Netz; Unsicherheit 
Abstract
Artificial neural networks (NNs) have become the de facto standard in machine learning. They allow learning highly nonlinear transformations in a plethora of applications. However, NNs usually only provide point estimates without systematically quantifying corresponding uncertainties. In this paper a novel approach towards fully Bayesian NNs is proposed, where training and predictions of a perceptron are performed within the Bayesian inference framework in closedform. The weights and the predictions of the perceptron are considered Gaussian random variables. Analytical expressions for predicting the perceptron’s output and for learning the weights are provided for commonly used activation functions like sigmoid or ReLU. This approach requires no computationally expensive gradient calculations and further allows sequential learning.