Juan Maldacena. The entropy of Hawking radiation and the information paradox
Online Conference ”Frontiers of holographic duality" April 27, 2020 16:00–17:00, Steklov Mathematical Institute, Moscow, online Juan Maldacena. The entropy ...
МЦМУ МИАН
Stéphane Mallat - Learning Physics with Deep Neural Networks (October 17, 2018)
More details: https://www.simonsfoundation.org/event/learning-physics-with-deep-neural-networks/
Simons Foundation
Gauge/gravity duality – Further insights and new applications:Modular flow and new Dirac materials
I will present two recent papers of our research group that are only very loosely related. The first part of my talk will be devoted to a new technique for evaluating ...
DIAS Dublin
Paper Review Call 021 - Learning spatiotemporal features with 3d convolutional networks
Join Karol Zak on a tour of video action detection using deep learning. Karol is going to cover off a breakthrough paper from 2015 "Learning spatiotemporal ...
Machine Learning Dojo with Tim Scarfe
Energy-based Approaches to Representation Learning - Yann LeCun
Workshop on Theory of Deep Learning: Where next? Topic: Energy-based Approaches to Representation Learning Speaker: Yann LeCun Affiliation: NYU and ...
Institute for Advanced Study
Leading order corrections to the quantum extremal surface prescription - Geoff Penington
High Energy Theory Seminar Topic: Leading order corrections to the quantum extremal surface prescription Speaker: Geoff Penington Affiliation: Stanford ...
Institute for Advanced Study
"Discontinuous Galerkin Methods for Hyerbolic PDEs: 1" - Olindo Zanotti
Computational Plasma Astrophysics: July 26, 2016 Prospects in Theoretical Physics is an intensive two-week summer program typically designed for graduate ...
Institute for Advanced Study
Jakob Hoydis - Recent Progress in End-to-End Learning for the Physical Layer
Abstract: End-to-end learning is one of the most promising applications of machine learning for the physical layer of communication systems. I will provide a ...
Institut des Hautes Études Scientifiques (IHÉS)
Machine learning the quantum many-body problem (Roger Melko)
Title: Machine learning the quantum many-body problem Abstract: The quantum wavefunction presents the ultimate "big data" problem in physics. When many ...
Brown University Department of Physics
ICTP-SISSA Colloquium: "What is Machine Learning, And What We Don't Understand About It"
Speaker: Prof. Andrea Montanari (Stanford University, USA) Abstract: The last fifteen years have witnessed dramatic breakthroughs in machine learning.
Int'l Centre for Theoretical Physics
CVPR 2019 Oral Session 1-2C: Scenes & Representation
0:43 d-SNE: Domain Adaptation using Stochastic Neighborhood Embedding Xiang Xu (University of Houston); Xiong Zhou (amazon); Ragav Venkatesan ...
ComputerVisionFoundation Videos
Mod-01 Lec-03 Dynamics in phase space
Lecture Series on Classical Physics by Prof.V.Balakrishnan, Department of Physics, IIT Madras. For more details on NPTEL visit http://nptel.iitm.ac.in.
nptelhrd
Deep Recurrent Inverse Modeling - Max Welling
Max Welling (University of Amsterdam) Invited Talk 1: Deep Recurrent Inverse Modeling for Radio Astronomy and Fast MRI Imaging Deep Learning for Physical ...
Deep Learning for Physical Sciences Workshop NIPS
Dr. Hector Zenil on Algorithmic Information Dynamics at AUTOMATA 2020
Special Session on Algorithmic Information Dynamics at AUTOMATA 2020 (https://www.automata2020.com/). 26th International Workshop on Cellular Automata ...
Hector Zenil
Lecture 6 Implicit Models / GANs part II --- CS294-158-SP20 Deep Unsupervised Learning -- Berkeley
Course homepage: https://sites.google.com/view/berkeley-cs294-158-sp20/home Instructors: Pieter Abbeel and Aravind Srinivas Course Instructors: Pieter ...
Pieter Abbeel
Artificial Intelligence in Radiology: Current Status and Trends Part 2
Check out deep learning page at https://www.CTisus.com Check out the apple app store for CTisus apps https://tinyurl.com/y2pyjzhv Keep in Touch at: ...
CTisus
Theory and Methods of Data Science
Scalable inference for a full multivariate stochastic volatility model Petros Dellaportas, Anastasios Plataniotis, Michalis Titsias University College London We ...
RoyalStatSoc
Modeling Perceptual Similarity and Shift-Invariance in Deep Networks
발표자: Richard Zhang (Adobe Research) 발표월: 2019.10. 더욱 다양한 영상을 보시려면 NAVER Engineering TV를 참고하세요. https://tv.naver.com/naverd2 ...
naver d2
Phase transitions: from physics to computer science
Phase transitions happen in complex systems, systems made of very many interacting entities, and correspond to a change of macroscopic state of the system ...
ICTP Mathematics
Max Welling - Make VAEs Great Again: Unifying VAEs and Flows
Abstract: VAEs and Flows are two of the most popular methods for density estimation. Well, actually GANs are more popular, but if we can show that VAEs and ...
London Machine Learning Meetup
Fall 2019 Robotics Seminar: NVIDIA Robotics Lab Part II
Presenters: Arsalan Mousavian & Nathan Ratliff with the NVIDIA Robotics Lab This video features the above presenters discussing the robotics research done at ...
Paul G. Allen School
Lenka Zdeborova - Phase transition in regression and simple neural networks
Institut des Hautes Études Scientifiques (IHÉS)
MIA: Geoffrey Schiebinger, Learning developmental landscapes with optimal transport; Lénaïc Chizat
September 27, 2017 Meeting: https://youtu.be/vJx7NiXFMi8?t=2499 Geoffrey Schiebinger Broad Institute, MIT Statistics Learning developmental landscapes ...
Broad Institute
Vittorio Ferrari - Recent research on 3D Deep Learning
July 14th - MIT CSAIL Abstract: I will present three recent projects within the 3D Deep Learning research line from my team at Google Research: (1) a deep ...
Vision Seminar MIT
Yann LeCun: "A Few (More) Approaches to Unsupervised Learning"
New Deep Learning Techniques 2018 "A Few (More) Approaches to Unsupervised Learning" Yann LeCun, New York University & Facebook DIrector of AI ...
Institute for Pure & Applied Mathematics (IPAM)
From GANs to Variational Divergence Minimization
An important problem in achieving general artificial intelligence is the data-efficient learning of representations suitable for causal reasoning, planning, and ...
Microsoft Research
The Information Knot Tying Sensing & Action; Emergence Theory of Representation Learning
Stefano Soatto ECE Seminar on Modern Artificial Intelligence.
NYU Tandon School of Engineering
AI Weekly Update - February 3rd, 2020 (#15)
Meena Chatbot: https://ai.googleblog.com/2020/01/towards-conversational-agent-that-can.html Curriculum for Reinforcement Learning: ...
Henry AI Labs
Top 10 Deep Learning Tips and Tricks - Arno Candel
Arno Candel, Chief Architect at H2O.ai H2O World 2015, Day 2 Join the Movement: open source machine learning software from H2O.ai, go to Github repository ...
H2O.ai
Deep Reinforcement Learning Part 2 - Volodymyr Mnih - MLSS 2017
This is Volodymyr Mnih's second talk of his lecture series, given at the Machine Learning Summer School 2017, held at the Max Planck Institute for Intelligent ...
Max Planck Institute for Intelligent Systems
High order path-conservative finite volume schemes for geophysical flows – M. Castro – ICM2018
Numerical Analysis and Scientific Computing | Mathematics in Science and Technology Invited Lecture 15.1 | 17.1 A review on high order well-balanced ...
Rio ICM2018
An Introduction to Computational Multiphysics II: Theoretical Background Part I
Mathematical formulation of multiscale/physics problems.
Harvard University
Sander Dieleman: Generating music in the raw audio domain
Realistic music generation is a challenging task. When machine learning is used to build generative models of music, typically high-level representations such ...
London Machine Learning Meetup
Michael Bronstein: "Deep functional maps: intrinsic structured prediction..."
New Deep Learning Techniques 2018 "Deep functional maps: intrinsic structured prediction for dense shape correspondence" Michael Bronstein, USI Lugano, ...
Institute for Pure & Applied Mathematics (IPAM)
Stanford CS330: Multi-Task and Meta-Learning, 2019 | Lecture 5 - Bayesian Meta-Learning
Assistant Professor Chelsea Finn, Stanford University http://cs330.stanford.edu/ To get the latest news on Stanford's upcoming professional programs in Artificial ...
stanfordonline
An invitation to tensor networks - Michael Walter
Computer Science/Discrete Mathematics Seminar II Topic: An invitation to tensor networks Speaker: Michael Walter Affiliation: University of Amsterdam Date: ...
Institute for Advanced Study
Insights on gradient-based algorithms in high-dimensional learning
Lenka Zdeborova, EPFL.
Physics Meets ML
Learning From and Dealing With Real, Rare World Data In Computer Vision
Computer Vision has achieved tremendous progress in recent years. Primarily because of the availability of massive datasets (e.g., ImageNet or the Yahoo ...
Microsoft Research
Deep Generative Models for Imitation Learning and Fairness
In the first part of the talk, I will introduce Multi-agent Generative Adversarial Imitation Learning, a new framework for multi-agent imitation learning for general ...
Microsoft Research
Risk Forum 2017 : le futur du deep learning en finance
Le développement rapide du deep learning révolutionne l'intelligence artificielle dans la collecte et la modélisation des données. Cette technologie ...
Institut Louis Bachelier
Deep Dive Into Computer Vision
Computer vision is the process of making computers detect and classify scenes, objects, and people. The presenter discusses different techniques, where things ...
Coding Tech
Recovery of ridge functions in the uniform norm – Sebastian Mayer, Universität Bonn
Many problems in science and engineering involve an underlying unknown complex process that depends on a large number of parameters. The goal in many ...
The Alan Turing Institute
