ALOP Colloquium with Dr. Benedikt Wilbertz

On November 28, 2016,  Dr. Benedikt Wilbertz will join the ALOP-Colloquium and present his recent work entitled

Hot Topics in Machine Learning

Abstract

The history of machine learning goes back to the late 50s, when the first perceptron models were created to build machines that lean from observations.

It took until the mid 80s that Yann LeCun constructed a neural network which can be considered as the first production read application of modern machine learning.

Since then, the field shifted its focus more towards statistics and probability theory, which gave birth to bagging, boosting and the random forest algorithm.

Only very recently and with the availability of huge training sets and the incredible computing power of GPGPU devices, neural networks had a massive comeback as Deep Learning methods and established many new state of the art results in for speech recognition, image analysis, natural language processing etc.

In this talk we give an overview over the recent developments in the field Deep Learning, but also present some new implementation of boosting algorithms and show some practical applications.

 At 15:45 there will be a coffee hour in E10. At 16:15 the presentation will take place in HS9.