Events

Mar 27 - Apr 3, 2022

Masterclass on Visual Computing

Dominik Michels, Helmut Pottmann, Ivan Viola, Peter Wonka, Soeren Pirk, Wolfgang Heidrich

Mar 29, 14:30 - Mar 30, 17:15

KAUST

visual computing

Visual Computing has become a key enabling technology for a diverse set of applications spanning scientific discovery, digital services, medicine, robotics, consumer electronics, and entertainment, to name just a few. The research community tackles problems in this vast space by drawing from expertise in multiple disciplines, including Computer Science, Electrical Engineering, and Mathematics. The KAUST Masterclass on Visual Computing highlights a selection of cutting-edge academic research within this field by comprising a series of talks focusing on different topics ranging from Computational Architecture and Fabrication, Deep Optics, and Generative Modeling, to Nanovisualization, Physics-based simulation, and Representation Learning.
Energy Efficient Neuromorphic computing systems

Khaled Salama, Professor, Electrical and Computer Engineering

Mar 28, 12:00 - 13:00

B9 R2322 H1

Traditional computing systems separate processors from memory, performing computation by shuttling data back and forth between these two units all the time. This bottleneck incurs limited processing speed and high power consumption in computing systems for deep learning models of ever-increasing complexity. Novel approaches and new principles are needed to revolutionize computing systems. Neuromorphic systems are proposed as a new computing architecture based on spiking neural networks analogous to the existing nervous systems.

Mar 20 - Mar 27, 2022

Permutation compressors for provably faster distributed nonconvex optimization

Peter Richtarik, Professor, Computer Science

Mar 21, 12:00 - 13:00

B9 R2322 H1

We study the MARINA method of Gorbunov et al (ICML 2021) - the current state-of-the-art distributed non-convex optimization method in terms of theoretical communication complexity. Theoretical superiority of this method can be largely attributed to two sources: the use of a carefully engineered biased stochastic gradient estimator, which leads to a reduction in the number of communication rounds, and the reliance on {\em independent} stochastic communication compression operators, which leads to a reduction in the number of transmitted bits within each communication round.

Mar 13 - Mar 20, 2022

Making Autonomous Driving more Reliable using Live 3D Digital Twins

Fawad Ahmad, PhD Candidate, Computer Science Department, University of Southern California

Mar 14, 18:30 - 19:30

KAUST

A live digital twin is a high-fidelity 3D representation of a physical object. This digital representation continuously replicates the physical object in real-time. My research vision is to build a live digital twin of the entire world. A live digital twin creates unprecedented capabilities for both computer and human consumption. It has the potential to improve safety and efficiency for autonomous driving, monitor on-going construction, and enable timely disaster relief operations etc. For humans, it means the possibility of digitally transporting to any place on the globe to live, interact and experience it in 3D like never before. These capabilities have strict performance and accuracy requirements. Achieving these requirements is not possible today for two reasons: limited wireless bandwidths, and limited on-board compute resources. I will talk about how I have tackled these challenges in my research to build end-to-end systems that build live digital twins and consume them for safer and more reliable autonomous driving. I will also discuss how I plan to implement my vision for building a live digital twin of the world in future.

Mar 6 - Mar 20, 2022

Feb 27 - Mar 6, 2022

Filling the Resources Gap with Approximate Mobile Computing

Veljko Pejović, Assistant professor at the Faculty of Computer and Information Science (UL FRI), University of Ljubljana, Slovenia

Feb 28, 12:00 - 13:00

B9 R2322 H1

Mobile computing proliferation is critically threatened by the breakdown of Dennard scaling, a law describing the area-proportional growth of integrated circuit power use.

Feb 20 - Feb 27, 2022

Computer Algebra in Scientific Computing

Dmitry Lyakhov, Research Scientist, Applied Mathematics and Computational Sciences

Feb 21, 12:00 - 13:00

B9 R2322 H1

In this talk I will speak about some recent theoretical advances in symbolic computation. In particular, exact computations with polynomials and differential equations will be discussed.

Feb 13 - Feb 27, 2022

When Second Order Methods Shine: Big Batches, Bayes, and Bilevel

Guodong Zhang, PhD student in University of Toronto

Feb 20, 15:00 - 16:00

KAUST

In this talk, I will discuss how the use of second-order information – e.g, curvature or covariance – can help in all three problems, yet with vastly different roles in each. First, I will present a noisy quadratic model, which qualitatively predicts scaling properties of a variety of optimizers and in particular suggests that second-order optimization algorithms would extend perfect scaling to much bigger batches. Second, I will show how we can derive and implement scalable and flexible Bayesian inference algorithms from standard second-order optimization algorithms. Third, I will describe a novel second-order algorithm that finds desired equilibria and save us from converging to spurious fixed points in two-player sequential games (i.e. bilevel optimization) or even more general settings. Finally, I will conclude how my research would pave the way towards intelligent machines that can learn from data and experience efficiently, reason about their own decisions, and act in our interests.

Feb 13 - Feb 20, 2022

Security and Resiliency for Critical Infrastructures

Professor Roberto Di Pietro, College of Science and Engineering, Cybersecurity at Hamad Bin Khalifa University

Feb 14, 12:00 - 13:00

B9 L2 R2322 H1

Our standard of living, nation GDP, and, in some cases, even our safety rely on critical infrastructures (CIs). In particular, being CIs generally perceived as a commodity (think of GPS availability, or avionics & maritime traffic routes and hubs), their security has largely been overlooked. The emergent property is that, nowadays, CIs systems are generally fragile, especially with respect to cyber attacks.

Feb 6 - Feb 13, 2022

Procedural Modeling of Botanical Trees

Wojtek Palubicki is leading the Natural Phenomena Modeling Group at the Faculty of Mathematics and Compter Science at the Adam Mickiewicz University in Poznan.

Feb 7, 12:00 - 13:00

KAUST

The exact mechanisms controlling plant growth are a topic of ongoing botanical research. This makes the realistic computer simulation of plants a challenging task. We present a method for generating realistic models of trees and shrubs. This method is based on the biological hypothesis that the form of a developing tree emerges from a self-organizing process dominated by the competition of buds and branches for light or space, and regulated by internal signaling mechanisms. Simulations of this process robustly generate a wide range of realistic trees and bushes.

Jan 30 - Feb 13, 2022

Safe and Secure Computer Control Systems? The devil is in the details...

Feb 6, 12:00 - 13:00

B9 L2 R2322 H1

In modern societies, there is an accelerated convergence of information technology (IT) like the internet-cloud-web complex, with operational technology (OT) like cyber-physical systems (CPS) control, complemented by Internet-of-Things fabrics (IoT).

Jan 30 - Feb 6, 2022

Jan 23 - Jan 30, 2022

Extensions of Dynamic Programming for Combinatorial Optimization and Data Mining - 2022-01-24

Mikhail Moshkov, Professor, Applied Mathematics and Computational Sciences

Jan 24, 12:00 - 13:00

KAUST

Dynamic programming is an efficient technique to solve optimization problems. It is based on decomposing the initial problem into simpler ones and solving these sub-problems beginning from the simplest ones.

Dec 5 - Dec 12, 2021

Deploying DNNs in the Embedded Space: Challenges and Opportunities

Christos-Savvas Bouganis, Reader in Intelligent Digital Systems in the Department of Electrical and Electronic Engineering, Imperial College London, UK

Dec 6, 12:00 - 13:00

B9 R2322 H1

The talk will discuss the challenging problem of designing Deep Neural Network systems that achieve high performance under low power envelopes, hindering their deployment in the embedded space.

Nov 28 - Dec 5, 2021

Nov 21 - Dec 5, 2021

Secure Dynamic Skyline Queries Using Result Materialization

Gabriel Ghinita, Associate Professor, University of Massachusetts, Boston

Nov 28, 12:00 - 13:00

B9 L2 R2322

Skyline computation is an increasingly popular query, with broad applicability to many domains. Given the trend to outsource databases, and due to the sensitive nature of the data (e.g., in healthcare), it is essential to evaluate skylines on encrypted datasets.

Nov 21 - Nov 28, 2021

Knowledge-based methods in bioinformatics

Robert Hoehndorf, Associate Professor, Computer Science

Nov 22, 12:00 - 13:00

B9 R2322 H1

The life sciences have invested significant resources in the development and application of semantic technologies to make research data accessible and interlinked, and to enable the integration and analysis of data. Utilizing the semantics associated with research data in data analysis approaches is often challenging. Now, novel methods are becoming available that combine symbolic methods and statistical methods in Artificial Intelligence. In my talk, I will show how to incorporate biological background knowledge in machine learning models for identification of gene-disease associations, genomic variants that are causative for heritable disorders, and to predict protein functions. The methods I describe are generic and can be applied in other domains in which biomedical ontologies and structured knowledge bases exist.

Nov 14 - Nov 21, 2021

Discrete geometric structures for architecture and and computational fabrication

Nov 15, 12:00 - 13:00

B9 R2322 H1

‌ Abstract Discrete differential geometry aims to develop discrete equivalents of notions and methods from smooth surface theory. It constitutes an area of active research in mathematics, but also provides effective methodology for a variety of applications. This talk will illustrate the fruitful interplay between theory and applications of discrete differential geometry at hand of selected topics in architectural geometry and computational fabrication. We discuss the construction of architectural freeform skins from flat, nearly rectangular panels, and associated support structures. These

Nov 7 - Nov 21, 2021

Towards Secure and Resilient Cyber-Physical Energy Systems - 2021-11-14

Charalambos (Harrys) Konstantinou, Associate Professor, Electrical and Computer Engineering

Nov 14, 12:00 - 13:00

KAUST

This talk will give an overview of the research of the Secure Next Generation Resilient Systems (SENTRY) lab (sentry.kaust.edu.sa) at KAUST.

Nov 7 - Nov 14, 2021

Oct 31 - Nov 7, 2021

Oct 24 - Oct 31, 2021

The Impact of Information Technology on the Future of Energy Consumption

Elmootazbellah Elnozahy, Professor (former), Computer Science

Oct 25, 12:00 - 13:00

B9 R2322 H1

The human race is facing what may turn out to be an existential threat due to entrenched practices that are contributing to climate change. This talk addresses the impact of information technology (IT) in this regard.

Oct 10 - Oct 17, 2021

The Data-sparse Renaissance in Numerical Linear Algebra

David Keyes, Senior Associate to the President, King Abdullah University of Science and Technology

Oct 11, 12:00 - 13:00

B9 R2322 H1

A traditional goal of algorithmic optimality, squeezing out operations, has been superseded because of evolution in architecture. Algorithms must now squeeze memory, data transfers, and synchronizations, while extra operations on locally cached data cost relatively little time or energy. Hierarchically low-rank matrices realize a rarely achieved combination of optimal storage complexity and high-computational intensity in approximating a wide class of formally dense operators that arise in exascale applications.

Oct 3 - Oct 10, 2021

Sep 26 - Oct 3, 2021

Towards Secure and Resilient Cyber-Physical Energy Systems - 2021-09-27

Charalambos Konstantinou, Assistant Professor, Computer Science, Electrical and Computer Engineering

Sep 27, 12:00 - 13:00

B9 R2322 H1

This talk will give an overview of the research of the Secure Next Generation Resilient Systems (SENTRY) lab (sentry.kaust.edu.sa) at KAUST. The transformation of critical infrastructures into cyber-physical systems contributes towards modernization allowing for better planning, more flexible control, system-wide optimization, etc. The security, however, of such systems presents significant challenges in controlling and maintaining secure access to critical system resources and services.

Sep 19 - Sep 26, 2021

Deep Optics - Joint Design of Imaging Hardware and Reconstruction Methods - Graduate Seminar

Wolfgang Heidrich, Professor, Computer Science

Sep 20, 12:00 - 13:00

B9 R2322 H1

Classical imaging systems are characterized by the independent design of optics, sensors, and image processing algorithms. In contrast, computational imaging systems are based on a joint design of two or more of these components, which allows for greater flexibility of the type of captured information beyond classical 2D photos, as well as for new form factors and domain-specific imaging systems. In this talk, I will describe how numerical optimization and learning-based methods can be used to achieve truly end-to-end optimized imaging systems that outperform classical solutions.

Sep 12 - Sep 26, 2021

Resilience is the Cybersecurity of the XXI century, and here's why! - 2021-09-19

Sep 19, 12:00 - 13:00

KAUST

In a nutshell, Resilient Computing is a new paradigm based on modelling, architecting and designing computer systems so that: they have built-in baseline defences; such defences cope with virtually any quality of threat, be it accidental faults, design errors, cyber-attacks, or unexpected operating conditions; provide incremental protection of, and automatically adapt to, a dynamic range of threat severity; provide sustainable operation. Resilient Computing will be a game changer in the craft of designing computer systems of today and future.

Sep 12 - Sep 19, 2021

A Journey in the Underwater Systems - Graduate Seminar

Basem Shihada, Professor, Computer Science

Sep 13, 12:00 - 13:00

B9 R2322 H1

In this seminar, I will go over our journey in the underwater networks research work. Basically, I will highlight our recent work on bringing the Internet to underwater environments by deploying a low power and compact underwater optical wireless system, called Aqua-Fi, that support today’s Internet applications.

Sep 5 - Sep 12, 2021

Aug 29 - Sep 5, 2021

Large-Scale Visualization of Scientific Data: Volume Data and Flow Fields - 2021-08-30

Markus Hadwiger, Professor, Computer Science

Aug 30, 12:00 - 13:00

B9 R2322 H1

This talk will give an overview of the research of the High-Performance Visualization research group (vccvisualization.org) at the KAUST Visual Computing Center (VCC). Interactive visualization is crucial to exploring, analyzing, and understanding large-scale scientific data, such as the data acquired in medicine or neurobiology using computed tomography or electron microscopy, and data resulting from large-scale simulations such as fluid flow in the Earth’s atmosphere and oceans. The amount of data in data-driven science is increasing rapidly toward the petascale and further.

Aug 8 - Aug 15, 2021

Stylistic and spatial disentanglement in GANs

Yazeed Alharbi, Ph.D., Computer Science

Aug 12, 14:00 - 16:00

KAUST

Computer Vision machine learning generative adversarial network Deep learning

This dissertation tackles the problem of entanglement in Generative Adversarial Networks (GANs). The key insight is that disentanglement in GANs can be improved by differentiating between the content, and the operations performed on that content. For example, the identity of a generated face can be thought of as the content, while the lighting conditions can be thought of as the operations.

Jun 20 - Jul 4, 2021

Artificial Intelligence methods for precision health: Applications to rare disease and cancer research

Robert Hoehndorf, Associate Professor, Computer Science

Jun 27, 10:00 - 11:00

B9 L2 H2

artificial intelligence

Abstract The life sciences have invested significant resources in the development and application of semantic technologies to make research data accessible and interlinked, and to enable the integration and analysis of data. Utilizing the semantics associated with research data in data analysis approaches is often challenging. Now, novel methods are becoming available that combine symbolic methods and statistical methods in Artificial Intelligence. In my talk, I will show how to incorporate biological background knowledge in machine learning models for the identification of gene-disease

Jun 13 - Jun 20, 2021

Reconfigurable Snapshot HDR Imaging Using Coded Masks

Masheal Alghamdi, Ph.D., Computer Science

Jun 17, 12:00 - 14:00

KAUST

High Dynamic Range (HDR) image acquisition from a single image capture, also known as snapshot HDR imaging, is challenging because the bit depths of camera sensors are far from sufficient to cover the full dynamic range of the scene. Existing HDR techniques focus either on algorithmic reconstruction or hardware modification to extend the dynamic range. In this thesis, we propose a joint design for snapshot HDR imaging by devising a spatially varying modulation mask in the hardware combined with a deep learning algorithm to reconstruct the HDR image. In this approach, we achieve a reconfigurable HDR camera design that does not require custom sensors, and instead can be reconfigured between HDR and conventional mode with very simple calibration steps. We demonstrate that the proposed hardware-software solution offers a flexible, yet robust, way to modulate per-pixel exposures, and the network requires little knowledge of the hardware to faithfully reconstruct the HDR image. Comparative analysis demonstrated that our method outperforms the state-of-the-art in terms of visual perception quality.

May 2 - May 9, 2021

Community Detection in Biological Networks: Lessons from the DREAM 2016 Module Identification Challenge

Lenore J. Cowen is a Professor in the Computer Science Department at Tufts University

May 3, 18:30 - 19:30

KAUST

The 2016 DREAM Disease Module Identification Challenge was developed to systematically assess the state of computational module identification methods on a diverse collection of molecular networks. Six different anonymized networks were presented with the gene names anonymized. The goal was to partition the genes into non-overlapping modules of from 3-100 genes each, based soley on the patterns of network connectivity.

Apr 25 - May 2, 2021

Energy-Efficiency and Security for EdgeAI: Challenges and Opportunities

Muhammad Shafique , Professor, Division of Engineering, New York University Abu Dhabi (NYU-AD), United Arab Emirates

Apr 26, 12:00 - 13:00

KAUST

Gigantic rates of data production in the era of Big Data, Internet of Thing (IoT), and Smart Cyber Physical Systems (CPS) pose incessantly escalating demands for massive data processing, storage, and transmission while continuously interacting with the physical world under unpredictable, harsh, and energy-/power-constrained scenarios. Therefore, such systems need to support not only the high-performance capabilities under tight power/energy envelop, but also need to be intelligent/cognitive and robust. This has given rise to a new age of Machine Learning (and, in general Artificial Intelligence) at different levels of the computing stack, ranging from Edge and Fog to the Cloud. In particular, Deep Neural Networks (DNNs) have shown tremendous improvement over the past years to achieve a significantly high accuracy for a certain set of tasks, like image classification, object detection, natural language processing, and medical data analytics. However, these DNN require highly complex computations, incurring huge processing, memory, and energy costs. To some extent, Moore’s Law help by packing more transistors in the chip.

Apr 18 - Apr 25, 2021

How do people explore virtual environments? Capturing and modeling visual behavior in VR

Belen Masia, Associate Professor in the Computer Science Department at Universidad de Zaragoza

Apr 19, 12:00 - 13:00

KAUST

Virtual Reality (VR) can dramatically change the way we create and consume content in areas of our everyday life, including entertainment, training, design, communication or advertising. Understanding how people explore immersive virtual environments is crucial for many applications in VR, such as designing content, developing new compression algorithms, or improving the interaction with virtual humans. In this talk, we will focus on how to capture and model visual behavior of users in virtual environments.

Apr 11 - Apr 18, 2021

Ingesting and Processing Data Efficiently for Machine Learning

Ana Klimovic, Assistant Professor, Systems Group of the Computer Science Department, ETH Zurich.

Apr 12, 12:00 - 13:00

KAUST

Machine learning applications have sparked the development of specialized software frameworks and hardware accelerators. Yet, in today’s machine learning ecosystem, one important part of the system stack has received far less attention and specialization for ML: how we store and preprocess training data. This talk will describe the key challenges for implementing high-performance ML input data processing pipelines.

Apr 4 - Apr 11, 2021

Challenges of Differentially Private Empirical Risk Minimization

Di Wang, Assistant Professor, Computer Science

Apr 5, 12:00 - 13:00

KAUST

Recent research showed that most of the existing machine learning algorithms are vulnerable to various privacy attacks. An effective way for defending these attacks is to enforce differential privacy during the learning process. As a rigorous scheme for privacy preserving, Differential Privacy (DP) has now become a standard for private data analysis. Despite its rapid development in theory, DP's adoption to the machine learning community remains slow due to various challenges from the data, the privacy models and the learning tasks. In this talk, I will give a brief introduction on DP and use the Empirical Risk Minimization (ERM) problem as an example and show how to overcome these challenges in DP model. Particularly, I will first talk about how to overcome the high dimensionality challenge from the data for Sparse Linear Regression in the local DP (LDP) model. Then, I will discuss the challenge from the non-interactive LDP model and show a series of results to reduce the exponential sample complexity of ERM. Next, I will present techniques on achieving DP for ERM with non-convex loss functions. Finally, I will discuss some future research along these directions.

Mar 28 - Apr 4, 2021

Mar 21 - Mar 28, 2021

Automated Reasoning in Systems Engineering

Laura Kovacs, Professor in Computer Science at the TU Wien

Mar 22, 12:00 - 13:00

KAUST

In this talk I will present recent advancement in automated reasoning, in particular computer-supported theorem proving, for generating and proving software properties that prevent programmers from introducing errors while making changes in this software. When testing programs manipulating the computer memory, our initial results show our work is able to prove that over 80% of test cases are guaranteed to have the expected behavior.

Mar 14 - Mar 21, 2021

On Discovering Nature’s Equations from Observations

Jesper Tegner, Professor, BESE Division, KAUST

Mar 18, 12:00 - 13:00

KAUST

In essence, science is about discovering regularities in Nature. It turns out that such regularities (laws) are written in the language of mathematics. In many cases, such laws are formulated and refined from fundamental “first principles.” Yet, in phenomenological areas such as biology, we have an abundance of data but lack “first principles.” Machine learning and deep learning, in particular, are remarkably successful in classification and prediction tasks. However, such systems, when trained on data, do not, as a rule, provide compact mathematical laws or fundamental first principles. Here we ask how we can identify interpretable compact mathematical laws from complex data-sets when we don’t have access to first principles. I will give an overview of this problem and provide some vignettes of our ongoing work in attacking this problem.