Machine Learning + X seminars are held byweekly.
Selected presentations from past seminars are posted blow. Yeonjong Shin

When multiscale computation, Parareal and PINN have a party by Zhen Li

SingleParticle Diffusion Characterization by Deep Learning by He Li

Image analysis and machine learning for detecting malaria by Shaoqing Yu

Can semantic inpainting inspire hydrogeologist? by Qiang Zheng

Vascular Network Structure and Its Transport Properties in Mouse Retina by Yosuke Hasegawa

RECURRENT NEURAL NETWORKS AND RESERVOIR COMPUTING FOR SPATIOTEMPORAL FORECASTING OF CHAOTIC DYNAMICS by Yang Liu
 Paper reviews: 1) Diagnosing Pregnancy Based on Wrist Pulse Wave, 2) Human Pulse Recognition based on Convolutional Neural Networks and 3) Wrist Pulse Signals Analysis based on Deep Convolutional Neural Network by Xiaoli Chen
 Deep learning observables in computational fluid dynamics by Ameya D. Jagtap
 Deep Learning for Ocean Remote Sensing: An Application of Convolutional Neural Networks for SuperResolution on SatelliteDerived SST Data by Xiang Li
 The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies by Guofei Pang
 Can PINNs beat FWI by Yiran Xu
 Graph Embedding method for Network data analysis by Mengjia Xu.
 Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness. Pengzhan Jin
 MoGlow: Probabilistic and controllable motion synthesis using normalising flows.
 Superresolution reconstruction of turbulent flows with machine learning.
 Fast and Scalable Bayesian Deep Learning by WeightPerturbation in Adam.
 Bridging Finite Element and Machine Learning Modeling: Stress Prediction of Arterial Walls in Atherosclerosis
 Deep relaxation: partial differential equations for optimizing deep neural networks.
 Data driven nonlinear dynamical systems identification using multistep CLDNN.
 Recent applications of neural networks in biological systems
 A synthetic turbulent inflow generator using machine learning
 Spectral Normalization for Generative Adversarial Networks
 Generative Modeling using the Sliced Wasserstein Distance.
 Sliced Wasserstein Generative Models.
 Understanding training and generalization in deep learning by Fourier analysis.
 An analysis of training and generalization errors in shallow and deep networks.
 Deep vs. Shallow Networks: an Approximation Theory Perspective.
 Predicting the solutions of heterogeneous elliptic PDEs with a confidence interval by probabilistic convolutional neural networks.
 Error bounds for approximations with deep ReLU neural networks in W^{s,p} norms.
 Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations .
 Assessment of EndtoEnd and Sequential Datadriven Learning of Fluid Flows.
 Boost your research through SciCoNet and SumsJob. Lu Lu
 An inverse problem framework for extracting phonon properties from thermal spectroscopy measurments . Mojtaba Forghani

A review of definitions of fractional derivatives and other operators. Ehsan Kharazmi

Paper Review: Optimal approximation of continuous functions by very deep ReLU networks. Dmitry Yarotsky


Mark ThachukDepartment of Chemistry, University of British Columbia, CanadaTitle: Coarse Graining Independent Particles using MoriZwanzig Theory

Ameya JagtapPaper Review:Artificial Neural Networks Trained Through Deep Reinforcement Learning Discover Control Strategies for Active Flow Control (arXiv:1808.07664v5)

Yeonjong ShinPaper Review: Elimination of all bad local minima in deep learning by Kenji Kawaguchi and Leslie Pack Kaelbling

Mojtaba ForghaniMechanical Engineering Department, MITTitle: An inverse problem framework for extracting phonon properties from thermal spectroscopy measurements.

Drew Linsley, Junkyung Kim & Thomas SerreTITLE: Recurrent neural networks for visual processing

Xiang LiTITLE: The Acquisition and Uncertainty Quantification of Land Surface Evapotranspiration at the Satellite Pixel Scale

Prof. Yosuke HasegawaTITLE: Vascular Network of Zebrafish Brain

Ludger Paehler, Technische Universität MünchenTITLE: Multifidelity and Machine Learning for Turbulent Flows

Alireza YazdaniTITLE: DataDriven Multiscale Modeling in Physical and Biological Systems

Dr. YuHang Tang,Lawrence Berkeley National LaboratoryTITLE:Prediction of atomization energy using graph kernel and active learning
 Guofei Pang  Paper Review: Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks by John Bradshaw, Alexander G. de G. Matthews, Zoubin Ghahramani
 Guofei Pang  Image recognition: Defense adversarial attacks using Generative Adversarial Network (GAN)
 Lu Lu  4 Years of Generative Adversarial Networks (GANs)
 Yanhui Su  Approximation theory in neural networks
 Zhiping Mao  Learning networks of stochastic differential equations
 Guofei Pang  When a neural net meets a Gaussian process