Michael Unser (EPFL) - The Radon transform, neural networks and splines Published 2022-05-02 Download video MP4 360p Download video MP4 720p Recommendations 1:01:35 Patrizio Frosini (University of Bologna) - Group equivariant non-expansive operators 58:08 "Optimal Transport for Statistics and Machine Learning" Prof. Philippe Rigollet, MIT 55:37 Andrea Manzoni (POLIMI) - Deep learning reduced order models for numerical approximation of PDEs 22:08 Biomedical Scientist Answers Pseudoscience Questions From Twitter | Tech Support | WIRED 20:40 How Many ERRORS Can You Fit in a Video?! 3:31:03 A conversation between Nassim Nicholas Taleb and Stephen Wolfram at the Wolfram Summer School 2021 13:44 Unexpected Discovery of Microbiome Inside Our Brains But Why Is It There? 1:05:11 Tomaso Poggio (MIT) - Thoughts on today’s learning theory 1:03:41 "Predictive Digital Twins: From physics-based modeling to scientific machine learning" Prof. Willcox 3:47:20 Math for Game Devs [2022, part 10] • Abstract Algebra, Procedural Animation & Splines 3:33:03 Deep Learning: A Crash Course (2018) | SIGGRAPH Courses 1:01:14 "On the Synergy of data and models for Virtualizing Structures & Infrastructure" Prof. Eleni Chatzi 46:02 Single cell transcriptomics - Cell type annotation (7 of 10) 1:04:53 Abdulle Lecture - Interactive theorem provers : can they help mathematicians ? - Prof. Kevin Buzzard 1:06:42 Single cell transcriptomics - Differential gene expression and Enrichment analysis (8 of 10) 3:55:49 SpaceX & NASA Launch U.S. Astronauts To Space | TIME 2:38:54 Tutorial: Biomedical Image Reconstruction—From Foundations To Deep Neural Networks, ICASSP 2020 35:05 NGS - Genome Variant analysis – Introduction to variant analysis (1 of 5) 2:27:29 Stephen Wolfram Readings: Why Does Biological Evolution Work? 17:17 Planck Stars: Alive Inside a Black Hole Similar videos 48:51 Michael Unser: "Splines and imaging: From compressed sensing to deep neural networks" 1:19:19 SPACE Webinar Series 3: Prof Michael Unser, EPFL 52:32 Michael Unser: Splines and Machine Learning: From classical RKHS methods to DNN (MLSP 2020 keynote) 50:44 EUSIPCO 2020 Keynote - Michael Unser "Deep splines" 37:03 Michael Unser - Advanced computational imaging: "Chassez le naturel, il revient au galop" 59:25 "New representer theorems for inverse problems and machine learning" Prof. Michaël Unser 42:53 M. Unser, Deep splines, Artificial Intelligence 2021 58:53 Richard Baraniuk: Deep Network Spline Geometry 38:34 Michael Unser: Wavelets and stochastic processes: how the Gaussian world became sparse 53:49 A Spline Perspective of Deep Learning - Richard Baraniuk - FFT Feb 28th, 2022 50:22 Michael Unser - Representer theorems for machine learning and inverse problems 1:00:52 Richard Baraniuk: Mad Max: Affine Spline Insights into Deep Learning 47:33 The mother of all representer theorems for inverse problems & machine learning - Michael Unser 1:11:46 Spline-based and isogeometric FEA: September 23, 2020 (Topic 3B) 1:03:53 Sophie Langer - Circumventing the curse of dimensionality with deep neural networks 36:51 Johannes Hertrich (TU Berlin) - Stochastic Normalizing Flows for Inverse Problems 14:23 Fast Quasi-harmonic Weights for Geometric Data Interpolation 1:14:49 One World SP(18/5/2022)--Prof. Robert D. Nowak (University of Wisconsin-Madison) More results