I’ll cover thee different RPC policies implemented on top of R2P2. Specifically, we’ll see how R2P2 enables efficient in-network RPC load balancing based on a novel  join-bounded-shortest-queue (JBSQ) policy. JBSQ lowers tail latency by centralizing pending RPCs in the middle box and ensures that requests are only routed to servers with a bounded number of outstanding requests. Then, I’ll talk about SVEN, an SLO-aware RPC admission control mechanism implemented as an R2P2 policy on P4 programmable switches. Finally, I’ll describe HovercRaft, a new approach to building fault-tolerant generic RPC services by integrating state-machine replication in the transport layer.

One of the main goals in computer vision is to achieve a human-like understanding of images. This understanding has been recently represented in various forms, including image classification, object detection, semantic segmentation, among many others. Nevertheless, image understanding has been mainly studied in the 2D image frame, so more information is needed to relate them to the 3D world. With the emergence of 3D sensors (e.g. the Microsoft Kinect), which provide depth along with color information, the task of propagating 2D knowledge into 3D becomes more attainable and enables interaction between a machine (e.g. robot) and its environment. This dissertation focuses on three aspects of indoor 3D scene understanding: (1) 2D-driven 3D object detection for single frame scenes with inherent 2D information, (2) 3D object instance segmentation for 3D reconstructed scenes, and (3) using room and floor orientation for automatic labeling of indoor scenes that could be used for self-supervised object segmentation. These methods allow capturing of physical extents of 3D objects, such as their sizes and actual locations within a scene.

In this dissertation, we aim at theoretically studying and analyzing deep learning models. Since deep models substantially vary in their shapes and sizes, in this dissertation, we restrict our work to a single fundamental block of layers that is common in almost all architectures. The block of layers of interest is the composition of an affine layer followed by a nonlinear activation function and then lastly followed by another affine layer. We study this block of layers from three different perspectives. (i) An Optimization Perspective. We try addressing the following question: Is it possible that the output of the forward pass through the block of layers highlighted above is an optimal solution to a certain convex optimization problem? As a result, we show an equivalency between the forward pass through this block of layers and a single iteration of certain types of deterministic and stochastic algorithms solving a particular class of tensor formulated convex optimization problems.

The Machine Learning Hub Seminar Series presents “Optimization and Learning in Computational Imaging” by Dr. Wolfgang Heidrich, Professor in Computer Science at KAUST. He leads the AI Initiative and is the Director of the KAUST Visual Computing Center. Computational imaging systems are based on the joint design of optics and associated image reconstruction algorithms. Historically, many such systems have employed simple transform-based reconstruction methods. Modern optimization methods and priors can drastically improve the reconstruction quality in computational imaging systems. Furthermore, learning-based methods can be used to design the optics along with the reconstruction method, yielding truly end-to-end learned imaging systems, blurring the boundary between imaging hardware and software.

In this thesis, a variety of applications in computer vision and graphics of inverse problems using tomographic imaging modalities will be presented: (i) The first application focuses on the CT reconstruction with a specific emphasis on recovering thin 1D and 2D manifolds embedded in 3D volumes. (ii) The second application is about space-time tomography (iii) Base on the second application, the third one is aiming to improve the tomographic reconstruction of time-varying geometries undergoing faster, non-periodic deformations, by a warp-and-project strategy. Finally, with a physically plausible divergence-free prior for motion estimation, as  well as a novel  view synthesis technique,  we present applications to dynamic fluid imaging which further demonstrates the flexibility of our optimization frameworks

The ML Hub, with the support of the AI Initiative, is excited to be hosting the AWS ML Immersion Day! Join us for a full-day immersion tutorial and hands-on lab on Amazon’s ML tools. The program includes an introduction to AWS AI and machine learning services and hands-on module on Amazon Lex and SageMaker. For details, please see the tutorial page on the ML Hub website. Registration is free but required. Please complete this form to register. Participants are encouraged to bring their fully-charged laptops and have a working Internet connection.

This talk will be a gentle introduction to proximal splitting algorithms to minimize a sum of possibly nonsmooth convex functions. Several such algorithms date back to the 60s, but the last 10 years have seen the development of new primal-dual splitting algorithms, motivated by the need to solve large-scale problems in signal and image processing, machine learning, and more generally data science. No background will be necessary to attend the talk, whose goal is to present the intuitions behind this class of methods.

Adil Salim is mainly interested in stochastic approximation, optimization, and machine learning. He is currently a Postdoctoral Research Fellow working with Professor Peter Richtarik at the Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST).

Abstract

Science communication is facing a p

Large-scale particle data sets, such as those computed in molecular dynamics (MD) simulations, are crucial to investigating important processes in physics and thermodynamics. The simulated atoms are usually visualized as hard spheres with Phong shading, where individual particles and their local density can be perceived well in close-up views. However, for large-scale simulations with 10 million particles or more, the visualization of large fields-of-view usually suffers from strong aliasing artifacts, because the mismatch between data size and output resolution leads to severe under-sampling of the geometry.

Abstract

The ability to create structural mo

Abstract

There are many intriguing aspects a

Materials science is a multidisciplinary field of research with many different scientists and engineers having various backgrounds active in it. The literature landscape consequently is populated currently by a wide range of journals which greatly differ in purpose, scope, quality, and readership. Jos Lenders, Deputy Editor of Advanced Materials, Advanced Functional Materials, and Advanced Optical Materials, will track some of the most important developments and trends in the research field and the Advanced journals program. Last year, Advanced Materials reached an Impact Factor of 21.95 and received over 8,300 submissions – and Advanced Functional Materials over 9,200. Only around 15% of all those papers made it to publication in the journal, and this rate is similar for all other Advanced journals. So, what do editors do to select the very best papers, and what can authors do to optimize their chances of having their manuscripts accepted?

This series of lectures guide students to the preparation and analysis of a well-organized abstract. We will discuss the proper language (tense, voice, and person) for abstract writing, and learn how to meet the purposes of different abstracts. Finally, students will have a chance to compose and evaluate their writing. Topics: Overview of abstract writing; Conference abstract journal abstract; Organization of an abstract; Language conventions of abstract writing; Disciplinary abstract analysis; Frequent mistakes of abstract writing.

Abstract

We are stumbling across a video tsunami flooding our communication channels.

Many problems in machine learning rely on statistics and optimization. To solve these problems, new techniques are needed. I will show some of these new techniques through selected machine learning problems I have recently worked on, such as nonconvex stochastic optimization, distributed training, adversarial attack, and generative models.

This work investigates the problem of transfer from simulation to the real world in the context of autonomous navigation. To this end, we first present a photo-realistic training and evaluation simulator Sim4CV which enables several applications across various fields of computer vision. Built on top of the Unreal Engine, the simulator features cars and unmanned aerial vehicles (UAVs) with a realistic physics simulation and diverse urban and suburban 3D environments. We demonstrate the versatility of the simulator with two case studies: autonomous UAV-based tracking of moving objects and autonomous driving using supervised learning.

With the ever-growing data sizes along with the increasing complexity of the modern problem formulations, there is a recent trend where heuristic approaches with unverifiable assumptions are overtaking more rigorous, conventional optimization methods at the expense of robustness. This trend can be overturned when we exploit dimensionality reduction at the core of optimization. I contend that even the classical convex optimization did not reach yet its limits of scalability.

The Open House is a great opportunity to see short presentations and demonstrations from recent research conducted in the Visual Computing Center. Join us and talk to KAUST faculty, students, and staff about research and applications of Visual Computing. You can explore the different areas of Visual Computing on your own or join one of the guided tours led by faculty and staff of the Visual Computing Center.

In this talk, I will introduce a few recent works on tree visualization. First I will present a  visualization technique for comparing topological structures and node attribute values of multiple trees. I will further introduce GoTree, a declarative grammar supporting the creation of a wide range of tree visualizations. In the application side, visualization and visual analytics on social media  will be introduced. The data from social media can be considered as graphs or trees with complex attributes. A few approaches using map metaphor for social media data visualization will be discussed.

Geometrically complex shapes play an increasingly important role in contemporary architecture. While digital models involving freeform geometry are easily created, the actual fabrication and construction of such structures remains a challenge. The workshop will brings together architects, engineers, construction managers, fabricators, researchers from the field of architectural geometry, and leading sustainability professionals to discuss, debate and share best practice on design, construction and the built environment.

The Cahn-Hilliard equation is a fourth order parabolic partial differential equation (PDE) that is widely used as a phenomenological model to describe the evolution of interfaces in many practical problems, such as, the microstructure formation in materials, fluid flow, etc. It has been observed in the engineering literature that the stochastic version of the Cahn-Hilliard equation provides a better description of the experimentally observed evolution of complex microstructure.