Deep learning

Aznaur Aliev

M.S. Student

Quantitative understanding of transcription factor regulation at network- and molecular-levels through optimization and deep learning

-

KAUST

Transcription factors are an important family of proteins that control the transcription rate from DNAs to messenger RNAs through the binding to specific DNA sequences. Transcription factor regulation is thus fundamental to understanding not only the system-level behaviors of gene regulatory networks, but also the molecular mechanisms underpinning endogenous gene regulation. In this talk, I will introduce our efforts on developing novel optimization and deep learning methods to quantitatively understanding transcription factor regulation at network- and molecular-levels. Specifically, I will talk about how we estimate the kinetic parameters from sparse time-series readout of gene circuit models, and how we model the relationship between the transcription factor binding sites and their binding affinities.

Overcoming the curse of dimensionality: from nonlinear Monte Carlo to deep learning

Arnulf Jentzen, Professor, Applied Mathematics Münster: Institute for Analysis and Numerics, University of Münster

-

KAUST

In this talk we prove that suitable deep neural network approximations do indeed overcome the curse of dimensionality in the case of a general class of semilinear parabolic PDEs and we thereby prove, for the first time, that a general semilinear parabolic PDE can be solved approximatively without the curse of dimensionality.

Deep Learning and Scientific Computing

-

B9 L2 R2322

In this talk, I will first give an elementary introduction to basic deep learning models and training algorithms from a scientific computing viewpoint. Using image classification as an example, I will try to give mathematical explanations of why and how some popular deep learning models such as convolutional neural network (CNN) work. Most of the talk will be assessable to an audience who have basic knowledge of calculus and matrix. Toward the end of the talk, I will touch upon some advanced topics to demonstrate the potential of new mathematical insights for helping understand and improve the efficiency of deep learning technologies.

On training algorithms for neural networks

-

B9 L2 R2322 H1

In this talk, I will first give a convergence analysis of gradient descent (GD) method for training neural networks by relating them with finite element method. I will then present some acceleration techniques for GD method and also give some alternative training algorithms

Bayesian Deep Learning

Maurizio Filippone, Associate Professor, EURECOM, France

-

B9 L3 R3128

The impressive success of Deep Learning (DL) in predictive performance tasks has fueled the hopes that this can help addressing societal challenges by supporting sound decision making. However, many open questions remain about their suitability to hold up to this promise. In this talk, I will discuss some of the current limitations of DL, which directly affect their wide adoption. I will focus in particular on the poor ability of DL models to quantify uncertainty in predictions, and I will present Bayesian DL as an attractive approach combining the flexibility of DL with probabilistic reasoning. I will then discuss the challenges associated with carrying out inference and specifying sensible priors for DL models. After presenting a few of my contributions to address these problems, I will conclude by presenting some interesting emerging research trends and open problems which define my current research agenda.

Optimization for Deep Learning

-

B5 L5 R5209

Abstract The field of optimization for machine learning has undergone significant changes in recent years with deep learning models increasing in scale and fine-tuning taking a more prominent role. In this presentation, I will share a perspective on the direction of changes in the field and highlight interesting research directions. I will provide real-world examples of what practitioners want from optimization methods to train deep networks at scale. I will then present my recent work on adaptive methods, such as Adam and Adagrad, and explain how we can estimate the learning rate for these

Dr. Harrou receives two IEEE ECBIOS 2021 best paper awards

1 min read ·
Dr. Fouzi Harrou, a research scientist in the KAUST Environmental Statistics (ES) group, recently received two IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability 2021 (IEEE ECBIOS 2021) best paper awards.

Deeper defense against cyber attacks

1 min read ·
To address the growing threat of cyberattacks on industrial control systems, a KAUST team including Fouzi Harrou, Wu Wang and led by Ying Sun has developed an improved method for detecting malicious intrusions.

Juncai He

I am currently a research scientist in Computer, Electrical and Mathematical Science and Engineering Division (CEMSE) at King Abdullah University of Science and Technology (KAUST). I received a B.S. degree in Mathematics and Applied Mathematics from Sichuan University in 2014. In the Summer of 2019, I received my Ph.D. degree in Computational Mathematics under the supervision of Prof. Jinchao Xu and Prof. Jun Hu at Peking University in Beijing, China. From 2019 to 2020, I worked as a Postdoctoral Scholar supervised by Prof. Jinchao Xu in The Center for Computational Mathematics and Application

Han Shao

Han Shao is a Ph.D. candidate at Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST), studying under the supervision of Professor Dominik Michels in Computational Sciences Group (CSG). Education and Early Career Han Shao obtained his bachelor degree in Theoretical and Applied Mechanics from The University of Science and Technology of China (USTC) in Hefei, China in 2014. After that, he joined KAUST and received his master degree in Mechanical Engineering in 2015. Research Interest Han is investigating the combustion phenomenon using CFD tools. For now

Aritra Dutta

Aritra Dutta is a Postdoctoral Research Fellow at the Extreme Computing Research Center (ECRC) in King Abdullah University of Science and Technology (KAUST), working with Professor Panagiotis Kalnis in his research group. Prior to that, he was a Postdoctoral Research Fellow in the Optimization and Machine Learning group of Professor Peter Richtárik. Education and Early Career Aritra Dutta received his bachelor degree in Mathematics (Hons.), Minor in Physics and Statistics from Presidency College in Calcutta University. He obtained a master degree in Mathematics and Computing from Indian