generative models

Mapping Properties of Neural Networks and Inverse Problems

Prof. Matti Lassas, Applied Mathematics, University of Helsinki, Finland

Feb 12, 18:00 - 19:00

B1 L4 R4214

Neural Networks generative models

This talk will explore the injectivity and universal approximation properties of neural networks, focusing on one-to-one mappings and the approximation of probability measures using compositions of invertible flow networks and injective layers, with applications in inverse problems, imaging, and generative models.

Xiaoqian Shen

Ph.D. Student, Computer Vision- Core Artificial Intelligence Research

generative models low-resource learning

Education Xiaoqian Shen is a Master's student at Vision-CAIR group in Visual Computing Center (VCC), King Abdullah University of Science and Technology (KAUST). • 2018-2022: BSc in Computer Science & Technology Dept. of Computer Science and Technology, Jilin University, China Research Interest • My research mainly focuses on leveraging natural language to facilitate better visual representation in a low-resource setting. Work Experience • Medical relation extraction for Chinese medicine instructions, 2021, Tsinghua University, China • Self-supervised Learning for medical image segmentation

Sherif Abdelkarim

Visiting Researcher, Computer Vision- Core Artificial Intelligence Research

Computer Vision generative models Deep learning swarm intelligence optimization

Current Sherif's reserach interests are in application of visual relationship understanding on long tail datasets. Education and Early Career Sherif obtained his bachelor's degree from the German University in Cairo (GUC), Egypt in 2013 in mechatronics engineering. Afterwards he attended MSc program of Intelligent Systems at Aberystwyth University, UK and where he graduated with distinction. Then Sherif worked as machine learning and deep learning engineer for multiple companies on a wide range of applications including customers' behavior clustering, object detection for self driving cars

Ivan Skorokhodov

Ph.D. Student, Computer Science

Deep learning Computer Vision generative models

Ivan Skorokhodov is a Ph.D. candidate in the Computer Science Program under the supervision of Professor Peter Wonka at Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST). His research interests include such areas of deep learning as generative models, hypernetworks and neural rendering. Ivan Skorokhodov has obtained his Ph.D degree and graduated in March 2023. Education and Early Career Ivan obtained his bachelor's degree in Management from the Moscow Engineering Physics Institute in 2014. He continued his studies there and received his master's degree