Explore cutting-edge research at the intersection of multimodal microscopy, deep learning, and mathematical modeling through this comprehensive workshop series. Discover how advanced computational techniques are revolutionizing the analysis of large-scale datasets generated by correlative electron, X-ray, optical, and scanning probe microscopes that provide chemical, structural, magnetic, and functional information at nano- and atomic scales. Learn about innovative approaches including compressed sensing, deep learning adaptations for microscopy applications, and simultaneous multimodal data processing techniques that extract maximum information from minimal data. Examine specific applications ranging from quantum phenomena in electron microscopy and atom-defined devices to medical image reconstruction and hyperspectral imaging enhancement. Gain insights into mathematical foundations including low-rank tensor recovery, signal recovery with generative priors, phase retrieval methods, and hierarchical tensor factorizations. Understand how machine learning is advancing scanning probe microscopy, STEM analysis of atomic behavior in liquids, and supervised/unsupervised approaches for electron microscopy data analysis. Explore the challenges and perspectives of deep learning in inverse problems, the role of data and models in image reconstruction, and motion imaging using microwave tones in MRI scanners. Bridge the gap between mathematics, physics, materials science, and engineering through presentations that demonstrate how interdisciplinary collaboration is advancing data acquisition, modeling, simulation, and analysis in multimodal microscopy research.

Syllabus

Naomi Ginsberg - Formation and function of assembled nanomaterials with multimodal X-ray scattering
Anna Little - Unbiasing Procedures for Scale-invariant Multi-reference Alignment - IPAM at UCLA
Hanbaek Lyu - Mesoscale reconstruction of images and networks using tensor decomposition
Michael Lustig - Multi-modal Motion Imaging using Microwave tones in an MRI scanner - IPAM at UCLA
Daniel Cremers - Deep Learning: Challenges and Perspectives - IPAM at UCLA
Rama Vasudevan - Advancing Microscopy with Machine Learning: Lessons from Scanning Probe Microscopy
Piotr Indyk - Learning-Based Low-Rank Approximations - IPAM at UCLA
Robert Wolkow - Atom-Defined Devices, Ultra-Fast Classical Devices, and Diverse Quantum Devices
Paul Hand - Signal Recovery with Generative Priors - IPAM at UCLA
Sarah Haigh - Probing atomic behaviour in liquids with STEM : opportunities for machine learning
Juan Carlos Idrobo - Quantum Phenomena & Electron Microscopy: New Possibilities & Limitations
Ben Recht - Splitting the difference between deep and shallow solutions of inverse problems
Mahdi Soltanolkotabi - Medical image reconstruction via deep learning: architectures, data reduction
Mary Scott - Supervised and Unsupervised approaches for Electron Microscopy Data Analysis
Elizaveta Rebrova - Low-rank tensor recovery from memory-efficient measurements - IPAM at UCLA
Mark Iwen - Accurate Recovery of Compactly Supported Smooth Functions from Spectrogram Measurements
Reinhard Heckel - The role of data and models for deep-learning based image reconstruction
Palina Salanevich - STFT Phase retrieval: robustness and generative priors - IPAM at UCLA
Kevin Kelly - Machine Learning Enhanced Compressive Hyperspectral Imaging - IPAM at UCLA
Jamie Haddock - Hierarchical and neural nonnegative tensor factorizations - IPAM at UCLA