Splitting the Difference Between Deep and Shallow Solutions of Inverse Problems
Explores balancing compressed sensing and deep learning in computational imaging, showcasing Plenoxels for efficient photorealistic view synthesis without neural networks.
Computational Imaging Systems: From DiffuserCam to Neural Activity Tracking - Seminar 2
Explore computational imaging systems, focusing on DiffuserCam technology and its applications in 3D neural activity tracking. Learn about challenges and solutions in image reconstruction and processing.
Solving Inverse Problems With Deep Neural Networks - Robustness Included?
Exploring robustness of deep learning in inverse problems, focusing on resilience against statistical noise and adversarial perturbations in image reconstruction tasks.
Theory of GANs for Compressed Sensing
Explore the theory of GAN priors in compressed sensing, covering key concepts, proofs, and optimization problems. Gain insights into visual representation and set restricted eigen value conditions.
Combinatorial Problems in Support Recovery for 1-bit Compressed Sensing
Explore advanced techniques in 1-bit compressed sensing, focusing on combinatorial approaches to support recovery and their applications in coding theory.
Masterclass for Optimisation - Professor Coralia Cartis, University of Oxford
Explore advanced optimization techniques for large-scale problems with Professor Coralia Cartis. Learn about algorithm development, analysis, and implementation for various problem classes in numerical optimization.
Applications of Sub-linear Algorithms in Other Fields
Explore how sub-linear algorithms impact diverse fields, enhancing efficiency and scalability in data analysis and problem-solving across disciplines.
What Physics Teaches Us About Computation in High Dimensions
Explore the intersection of physics and high-dimensional computation, uncovering insights on phase transitions, algorithms, and deep learning in this thought-provoking lecture by Lenka Zdeborová.
Quantum Phase Estimation by Compressed Sensing
Explore innovative techniques for quantum phase estimation using compressed sensing, enhancing accuracy and efficiency in quantum information processing.
Photorealistic Reconstruction from First Principles
Explore photorealistic reconstruction techniques combining compressed sensing and deep learning for computational imaging, focusing on recovering optical density and view-dependent color from calibrated photographs.
Big Data Inverse Problems - Promoting Sparsity and Learning to Regularize
Explore novel methods for solving big data inverse problems, focusing on sparse representation and L1 regularization. Learn about variable projection and deep neural networks for parameter optimization.
The Mathematical Foundations of Deep Learning: From Rating Impossibility to Practical Existence Theorems
Explorez les fondements mathématiques de l'apprentissage profond, de l'impossibilité de notation aux théorèmes d'existence pratique. Découvrez les défis et les avancées dans ce domaine en pleine expansion.