Explainable machine learning for the environmental sciences. Prof.Dr.-Ing. Ribana Roscher.06.08.2021
Machine learning methods have been an integral part of many application areas for some time. Especially with the recent development of neural networks, these methods are increasingly used in the sciences to obtain scientific results from observational or simulation data. Besides high accuracy, a desired goal is to learn explainable models and to understand how a specific decision was made. To achieve this goal and obtain explanations, knowledge from the domain is needed, which can be integrated into the model or applied post-hoc. This presentation addresses explainable machine learning approaches in the environmental sciences and shows that machine learning can not only be used to learn models that should be consistent with our existing knowledge but can also lead to new scientific insights.
Видео Explainable machine learning for the environmental sciences. Prof.Dr.-Ing. Ribana Roscher.06.08.2021 канала International Future AI Lab AI4EO TUM
Видео Explainable machine learning for the environmental sciences. Prof.Dr.-Ing. Ribana Roscher.06.08.2021 канала International Future AI Lab AI4EO TUM
Показать
Комментарии отсутствуют
Информация о видео
11 августа 2021 г. 13:50:16
01:05:09
Другие видео канала
Large-scale spatio-temporal indexing & analytics with IBM PAIRS. Dr Conrad Albrecht. 11.06.2021Data-driven Machine Vision for Fast and Reliable Predictions by Rudolph TriebelInterpretable Deep Learning from Earth Observation Data, Prof. Dr. Plamen AngelovFrom Compressed Sensing to Neurally Augmented Algorithms. Dr. Peter Jung. 22th January 2021.Geospatial Machine Learning for Earth Observation and Climate Modeling. Konstantin Klemmer. 02.07.21Unsupervised deep learning for multi-temporal analysis. Dr. Sudipan Saha. 10th December. 2020Towards Geographically-Aware Machine Learning. Konstantin Klemmer. 4th November 2020Semantic Segmentation & Detection Using Multi-Sensory Data by Dr. Muhammad ShahzadChallenges of predicting sea level rise & potential consequences for society, Prof. Jonathan BamberInternationale Zukuftslabore - Zukuftslabor AI4EO / International Future Labs - Future Lab AI4EOANN and AI in high Assurance Applications: Gaps and TechniquesBeyond Perception Towards Reasoning: Visual Reasoning in Remote Sensing. Prof. Dr Lichao Mou. 29.OctDealing with Data-related Problems in Learning-based Artificial Intelligence. Dr. Peter Roth.12.02.ML to approach sustainability using scarcely labeled to unlabeled EO data, Prof. Dr. Dario OliveiraOn the bias of some popular EO datasetsData-driven Machine Vision for Fast and Reliable PredictionsInternationale Zukunftslabore - Was ist KI? / International Future Labs - What is AI?