Machine Learning + X Seminars 2019 – The Crunch Group

December 20, 2018: Neural Ordinary Differential Equations by Liu Yang
December 20, 2018: A Proposal on Machine Learning via Dynamical Systems Liu Yang
December 20, 2018: Identification of distributed parameter systems – A neural net based approach Liu Yang
December 14, 2018: Spectral penalty method for the two-sided fractional differential equations with general boundary conditions by Nan Wang, Farewell
December 14, 2018: Adversarial Uncertainty Quantification in Physics-Informed Neural Networks by Dongkun Zhang
November 30, 2018: Indentification of physical processes via data-driven and data-assimilation methods by Xuhui Meng
November 30, 2018: Predicting Bending Displacement of IPMC Actuators Using Parallel Non-Autoregressive Recurrent Neural Networks by Guofei Pang
November 16, 2018: Hidden Physics Models: Machine Learning of Non-Linear Partial Differential Equations by Maziar Raissi
November 16, 2018: Background, Clinical Features and Pathogenesis of Diabetic Retinopathy by He Li
November 9, 2018: An introduction to multi-fidelity ensemble smoother and my ongoing projects by Qiang Zheng
November 9, 2018: Collapse of Deep and Narrow Neural Nets by Lu Lu
October 19, 2018: Estimation of turbulent channel flow based on wall measurements by Zhichen Liu, University of Tokyo
October 19, 2018: Machine Learning with observers predicts complex spatiotemporal behavior by Liu Yang
October 5, 2018: Altered blood rheology and impaired pressure-induced cutaneous vasodilation in a mouse of combined type 2 diabetes and sicle cell trait by He Li
October 5, 2018: Analysis of prediction accuracy of classification problem based on neural networks by Lu Lu
September 28, 2018: Spectral Fractional Diffusion: Well-posedness, Steady State, and Stochastic Solution Formulas by Mamikon Gulian
September 28, 2019: Physical informed kriging (Phik) and Gradient-enhancing cokriging (GECK) — paper review and summer project report by Yi-xiang Deng
August 28, 2018: Kernel Flows: from learning kernels from data into the abyss by Guofei Pang
August 3, 2018: Multi-level multi-fideity sparse polynomial chaos expansion based on Gaussian process regression by Dongkun Zhang
August 3, 2018: Neural Networks 101: Implementing feedforward Neural Nets using TensorFlow by Lu Lu
June 8, 2018: Exponential expressivity in deep neural networks through transient chaos by Yang Liu
June 8, 2018: Deep and confident prediction for time series at Uber by Yang Liu
June 8, 2018: GANGs: Generative adversarial network games by Yang Liu
May 18, 2018: Doing the impossible: Why neural networks can be trained at all by Anna Lischke
May 18, 2018: Deep Relaxation: partial differential equations for optimizing deep neural networks by Mamikon Gulian
May 11, 2018: Deep Neural Network as Gaussina Process by Guofei Pang
April 20, 2018: Optimal Control of momentum and scalar transfer ~ Turbulance control, shape/topology optimization, remodeling of vascular network~ by Yosuke Hasagawa
March 30, 2018: Learning networks of stochastic differential equations by Zhiping Mao
March 2, 2018: Approximate Bayes learning of stochastic differential equations by Ansel Blumers & Xhen Li
February 16, 2018: 4 Years of Generative Adversarial Networks (GANs) by Lu Lu
February 16, 2019: The Robust Manifold Defense: Adversarial Training using Generative Models by Guofei Pang
February 2, 2018: Non-intrusive reduced order modeling of nonlinear problems using neural networks by Anna Lischke
January 19, 2018: Brief introduction to several common neural networks by Liu Yang
January 19, 2018: An effcient deep learning technique for the Navier-Stokes equations: Application to unsteady wake flow dynamics by Dongkun Zhang