This event will be hosted by SAP who also will offer snacks and drinks. Thanks SAP for having us!
Talk 1: The Faces of Nanomaterials: Insightful Perfect Classification using Deep Learning (45 min)
Speaker: Dr. Angelo Ziletti, Deputy Group Leader Fritz Haber Institute of the Max Planck Society, Berlin
Abstract: Computational methods that extract knowledge from materials science data are critical for enabling the data-driven discovery of novel nanomaterials for technological applications. A reliable identification of the crystal type is a crucial first step for materials characterization and analytics. Current methods require a user-specified threshold, and are unable to identify the correct crystal type for defective structures. Here, we introduce a new machine-learning-based approach to automatically classify nanomaterials by their crystal structure. First, we represent materials by a diffraction image, and then construct a deeplearning neural-network model for classification. Our approach is able to correctly classify a dataset comprising more than 80,000 structures, including heavily defective ones. The internal operations of the neural network are unraveled through attentive response maps, demonstrating that it uses the same landmarks a materials scientist would use, although never explicitly instructed to do so.
Talk 2: Applying advanced deep learning techniques to analyze financial documents
Speaker: Dr. Johannes Höhne, Senior Data Scientist in the Deep Learning Center of Excellence, Innovation Center Network of SAP.
Bio: Prior to joining SAP Johannes has been a co-founder of a bajomi analytics start-up which was acquired by excentos Software GmbH. Johannes has been dealing with data-related problems for the past seven years, aiming to understand and solve problems by means of data analysis. The passion for data gave him insights into various domains such as Finance, Neuroscience, E-commerce or Bioinformatics. Besides his interest in data, he is driven by an entrepreneurial spirit enabling eﬃcient prototyping and "lean" development cycles. After his university education in Berlin and Sydney, Johannes pursued a scientiﬁc career in the ﬁeld of Neurotechnology and Machine Learning obtaining a PhD degree from TU Berlin.