Dr. Maja Rudolph(Bosch Center for Artificial Intelligence, Pittsburgh)
hosted by Machine Learning Group of Prof. Marius Kloft
"Self-Supervised Learning beyond Images and Text"
Self-supervised learning has emerged as a powerful paradigm for machine learning,especially for drawing insights from unlabeled data.The key idea is to introduce auxiliary prediction tasks and to train a deep model to solve these auxiliary tasks.If the tasks are designed well, the trained model will be useful for a number of purposessuch as anomaly detection, feature extraction, and forecasting.Unfortunately, most successful approaches for SSL rely on domain-specific indictive biasesand are therefore limited to individual use-cases. In this talk, I present advanced self-supervised learning lossesthat facilitate domain-general self-supervised learning beyond images and text.Exponential family embeddings, for example, generalize word embeddings to provide insight into a wide range of applications.They are a useful tool for studying zebrafish brains in neuro science, for studying shopping behavior in economics,or for studying language evolution in computational social science.Similarly, neural transformation learning (NTL), is a new general-purpose tool for self-supervised anomaly detection.While related methods in computer vision typically require image transformations such as rotations, blurring, or flipping,NTL automatically learns the best transformations from the data and therefore generalizesself-supervised AD to almost any data type.
Bio: As a Senior Research Scientist at the Bosch Center for AI, Maja Rudolph develops machine learning methodsfor drawing valuable insights from unlabeled, noisy data. The domain-general methods she has developed can be usedto identify interpretable patterns, form scientific theories, and detect anomalies.She holds a Ph.D. in computer science from Columbia University and a BS in mathematics from MIT.
|Time:||Thursday, 09.02.2023, 14:00|