Events List

DateEvent TypeSpeaker
10/01/2018CCPP Brown BagDavid Hogg [ + ]
10/01/2018Blanton Tinker Pullen Blanton Tinker Pullen [ + ]
10/01/2018Informal Astro TalkJaiyul Yoo [ + ]
10/02/2018Modjaz Group MtgModjaz Group Mtg [ + ]
10/02/2018Astro SeminarJeremiah Murphy [ + ]
10/03/2018Astroparticle Group MeetAstro Particle Group Mtg [ + ]
10/03/2018HEP SeminarConnor Behan [ + ]
10/03/2018Astro PhAstro Ph [ + ]
10/04/2018Physics Dept ColloquiumWill Farr [ + ]
10/05/2018SPS Mentor MixerSPS Mentor/Mentee Mixer [ + ]
10/05/2018NYU-CCA LSS Group MtgNYU-CCA LSS Group Mtg [ + ]
10/05/2018Grad Student SympGraduate Student Symposium [ + ]
10/08/2018No Brown Bag [ + ]
10/08/2018Blanton Tinker Pullen Blanton Tinker Pullen [ + ]
10/09/2018Modjaz Group MtgModjaz Group Mtg [ + ]
10/09/2018Astro SeminarElisa Chisari [ + ]
10/10/2018Astroparticle Group MeetAstro Particle Group Mtg [ + ]
10/10/2018HEP SeminarJacob Sonnenschein [ + ]
10/10/2018Astro PhAstro Ph [ + ]
10/11/2018Physics Dept ColloquiumMichel Devoret [ + ]
10/12/2018MacFadyen Group MtgMacFadyen Group Mtg [ + ]
10/12/2018Astro PhAstro Ph [ + ]
10/12/2018ISCISC [ + ]
10/15/2018CCPP Brown BagMassimo Porrati [ + ]
10/15/2018Blanton Tinker Pullen Blanton Tinker Pullen [ + ]
10/16/2018Modjaz Group MtgModjaz Group Mtg [ + ]
10/16/2018Astro SeminarAndrey Timokhin [ + ]
10/16/2018Special SeminarAlex Vilenkin [ + ]
10/17/2018Astroparticle Group MeetAstro Particle Group Mtg [ + ]
10/17/2018HEP SeminarJesse Thaler [ + ]
10/17/2018Astro PhAstro Ph [ + ]
10/18/2018Physics Dept ColloquiumEric Vanden Eijnden [ -- ]

Title: Machine Learning, Particle Systems and Scientific Computing
Description: The methods and models of machine learning (ML) are rapidly becoming de facto tools for the analysis and interpretation of large data sets. Complex classification tasks such as speech and image recognition, automatic translation, decision making, etc. that were out of reach a decade ago are now routinely performed by computers with a high degree of reliability using (deep) neural networks. These performances suggest that it may be possible to represent high-dimensional functions with controllably small errors, potentially outperforming standard interpolation methods based on Galerkin truncation or finite elements: these have been the workhorses of scientific computing but suffer from the curse of dimensionality. By beating this curse, ML techniques could change the way we perform quantum physics calculations, molecular dynamics simulation, PDE solution, etc. In support of this prospect, in this talk I will present results about the representation error and trainability of neural networks, obtained by mapping the parameters of the neural network to a system of interacting particles. I will also discuss what these results imply for applications in scientific computing. (4:00 PM - 5:00 PM, 726 Broadway, 940, CCPP Seminar)
10/19/2018NYU-CCA LSS Group MtgNYU-CCA LSS Group Mtg [ + ]
10/19/2018Special HET SeminarAlessandro Sfondrini [ + ]
10/19/2018ISCISC [ + ]
10/22/2018CCPP Brown BagAnthony Pullen [ + ]
10/22/2018Informal Astro TalkGabrijela Zaharijas [ + ]
10/22/2018Blanton Tinker Pullen Blanton Tinker Pullen [ + ]
10/23/2018Modjaz Group MtgModjaz Group Mtg [ + ]
10/23/2018Astro SeminarMatteo Cantiello [ + ]
10/24/2018Astroparticle Group MeetAstro Particle Group Mtg [ + ]
10/24/2018HEP SeminarEliezer Rabinovici [ + ]
10/24/2018Astro PhAstro Ph [ + ]
10/25/2018Physics Dept ColloquiumMariangela Lisanti [ + ]
10/26/2018ISCISC [ + ]
10/29/2018CCPP Pizza SocialPizza [ + ]
10/29/2018Blanton Tinker Pullen Blanton Tinker Pullen [ + ]
10/30/2018Modjaz Group MtgModjaz Group Mtg [ + ]
10/30/2018Astro SeminarMichele Bannister [ + ]
10/31/2018Astroparticle Group MeetAstro Particle Group Mtg [ + ]
10/31/2018HEP SeminarChris Hull [ + ]
10/31/2018Astro PhAstro Ph [ + ]