Deep learning

Najmeddine Dhieb

Najmeddine Dhieb

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.

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.

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.

KAUST Prospective Student: Damilya Saduakhas

1 min read ·
Damilya Saduakhas, 21 years old, from Kazakhstan, obtained a B.Sc. degree in mathematics from the Nazarbayev University, Kazakhstan. Damilya has been selected as a young scientist to participate in the summer Data Lab from Yessenov Foundation and will join KAUST in the fall of 2020 as an M.S./Ph.D. candidate in the KAUST Stochastic Processes and Applied Statistics Research group under the supervision of Professor David Bolin.

KAUST Environmental Statistics group publishes book exploring multivariate statistical analysis

1 min read ·
The KAUST Environmental Statistic (ES) research group has recently published a book titled "Statistical Process Monitoring Using Advanced Data-Driven and Deep Learning Approaches." The book is the outcome of the Core Research Grant (GRG) project led by KAUST Professor Ying Sun, Associate Professor of Statistics.

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.

Meet KAUST new student: Qilong Pan

1 min read ·
Qilong Pan is a statistics graduate who joined KAUST in June 2021 from the Wuhan University of Technology, China. Pan is a M.S./Ph.D. student and member of the Environmental Statistics research group under the supervision of Professor Ying Sun.

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.

Qilong Pan

Ph.D. Student, Statistics
Qilong Pan is a MS/Ph.D. student in the Environmental Statistics group under the supervision of Prof. Ying Sun at the King Abdullah University of Science and Technology (KAUST). He believes that life and study at KAUST would be an unforgettable experience for his whole life. Education and early career B.S. in Statistics in 2021, Wuhan University of Technolgy B.A. in English in 2021, Huazhong University of Science and Technology Research Interests Environmental statistics, Spatio-temporal statistics, Deep Learning

Maurizio Filippone

Associate Professor, Statistics
KAUST Associate Professor of Statistics Maurizio Filippone’s primary research focus is Bayesian statistics, namely, enabling sound decision-making through uncertainty quantification in model parameters and predictions. His main research interests are in models based on deep learning and Gaussian processes

Matthew Sainsbury-Dale

Postdoctoral Research Fellow, Statistics
Matthew obtained his PhD in 2024 from the University of Wollongong (UOW), Australia, with a thesis titled "Efficient Inference for Spatial and Spatio-Temporal Statistical Models Using Basis-Function and Deep-Learning Methods", which received the Examiners Commendation for Outstanding Thesis. He is now a postdoctoral researcher at the King Abdullah University of Science and Technology (KAUST), working in the XSTAT group under Prof. Raphaël Huser's supervision. Education and Early Career Matthew obtained his PhD in 2024 from the University of Wollongong (UOW), Australia. He joined KAUST as a

Malik Shahid Sultan

Ph.D. Student, Statistics
Malik Shahid Sultan is a Ph.D. student in Bio-Engineering ( Bioinformatics & Machine Learning) at the King Abdullah University of Science and Technology (KAUST), studying under the supervision of Professor Hernando Ombao in the Biostatistics group. Education and Early Career Malik Shahid Sultan hold BSc. in Industrial Engineering with a Gold Medal from the University of Engineering and Technology Taxila (Pakistan). Malik holds M.Sc. from King Abdullah University of Science and Technology (KAUST) (Saudi Arabia) in Bio-Engineering (Bioinformatics & Machine Learning). During the Fall of 2021

Amine Bejaoui

Amine Bejaoui was an MS/Ph.D. student in the Communication Theory Lab (CTL) under the supervision of Professor Mohamed-Slim Alouini at King Abdullah University of Science and Technology (KAUST). Education and Early Career Amine Bejaoui obtained his engineering degree with majors in Economics and Scientific management from Ecole Polytechnique de Tunisie (EPT) , Tunisia, in 2015. Research Interest The scientific interests of Amine Bejaoui lies in the area of statistics, machine learning and the applications of Random Matrix Theory. Education Profile M.Sc. in Statistics, KAUST, Aug 2018 – Present