• Speaker: Liping Yin, MSU
• Title: Long Range Constraints for Neural Texture Synthesis Using Sliced Wasserstein Loss
• Date: 11/21/2022
• Time: 1:00 PM - 2:00 PM
• Place: C117 Wells Hall (Virtual Meeting Link)
• Contact: Craig Gross (grosscra@msu.edu)

In the past decade, exemplar-based texture synthesis algorithms have seen strong gains in performance by matching statistics of deep convolutional neural networks. However, these algorithms require regularization terms or user-added spatial tags to capture long range constraints in images. Thus, we propose a new set of statistics for exemplar based texture synthesis based on Sliced Wasserstein Loss and create a multi-scale algorithm to synthesize textures without any regularization terms or user-added spatial tags. Lastly, we study the ability of our proposed algorithm to capture long range constraints in images and compare our results to other exemplar-based neural texture synthesis algorithms. $\\$ This will be a hybrid seminar and take place in C117 Wells Hall and via Zoom at https://msu.zoom.us/j/99426648081?pwd=ZEljM3BPUXg2MjVUMVM5TnlzK2NQZz09 .

• Speaker: Lucas Hall, MSU
• Title: Modular Stone-von Neumann Theorems
• Date: 11/21/2022
• Time: 4:00 PM - 5:30 PM
• Place: C517 Wells Hall
• Contact: Brent Nelson (banelson@msu.edu)

I’ll talk about C*-modules and representations on them, developing a loose parallel with the Hilbert space case. For specialized C*-modules, much can be said, and a classification of these modules suggests a vast generalization of the Stone-von Neumann Theorem which accommodates all of the data of generalized C*-dynamical systems.