Cluster Grid

The summer-school will host five guest presentations as follows in room EF207:

On June the 24th we will have Razvan Dobre from Adobe presenting at 10AM Openstack, which is currently the largest opensource platform used in Cloud Computing. Among its developers we number RedHat, IBM, HP, Intel, Rackspace, etc. The presentation is available here:    2014.06.24 - Razvan Dobre - Openstack

On June the 25th we will have Marius David from IBM/Lenovo at 10AM presenting VMWare technologies as follows: 

• Introduction - what is virtualization
• Server Virtualization
• Virtual networking
• Making the network VM-Aware with VMReady
• VMReady Security – MAC Spoofing prevention – VMCheck
• Standardized VM-Aware networking with 802.11 QBG

The presentations are available here:  2014.06.25 - VMReady_QBG  2014.06.25 - Implementing a VM-Aware Network Using VMready

• OpenCL theoretical presentation
• OpenCL hands-on: matrix multiplication, image processing (if it fits the schedule)
• Performance of the cache & memory subsystem (theory & hands-on)
• Defining and analyzing performance. Performance optimizations. (theory & hands-on)

The presentations are available here:  2014.06.26 - Adrian Loteanu - Cache Performance  2014.06.26 - Adrian Loteanu - Performance and Optimization  2014.06.26 - Radu Velea - OpenCL Summer School

On July the 8th we will have Dr. Marius Leordeanu from IMAR presenting at 2:30PM Computer Vision - Boundary Detection Algorithms:

Boundary detection is a fundamental computer vision problem that is essential for a variety of tasks, such as contour and region segmentation, symmetry detection and object recognition and categorization. I will present our generalized formulation for boundary detection, with closed-form solution, applicable to the localization of different types of boundaries, such as object edges in natural images and occlusion boundaries from video. Our generalized boundary detection method (Gb) simultaneously combines low-level and mid-level image representations in a single eigenvalue problem and solves for the optimal continuous boundary orientation and strength. The closed-form solution to boundary detection enables our algorithm to achieve state of the art results at a significantly lower computational cost than current methods. We also propose two complementary novel components that can seamlessly be combined with Gb: first, we introduce a soft-segmentation procedure that provides region input layers to our boundary detection algorithm for a significant improvement in accuracy, at negligible computational cost; second, we present an efficient method for contour grouping and reasoning, which when applied as a final post-processing stage, further increases the boundary detection performance.

Webpage with more details, papers and code: https://sites.google.com/site/gbdetector/

Marius Leordeanu is a senior research scientist at the Institute of Mathematics of the Romanian Academy and adjunct professor at University Politehnica of Bucharest, where he teaches graduate level Computer Vision. Marius received his Ph.D. in Robotics from Carnegie Mellon University in 2009 and Bachelor degrees in Mathematics and Computer Science from the City University of New York, in 2003. His research focuses on computer vision and machine learning, with contributions to learning and optimization for matching and probabilistic graphical models,
object category recognition, object tracking, 3D modeling of urban scenes, video understanding, human activity recognition and image boundary detection.

Homepage: https://sites.google.com/site/mariusleordeanu/

The presentation is available here:  2014.07.08 - MariusLeordeanu - Generalized Boundary Detection from Multiple Image Interpretations

On July the 10th we will have Cristi Cojocaru from HP presenting at 10AM "HPC in the future".

The presentations are available here:   2014.07.10 - Cristian Cojocaru - 1 Intro to HPC  2014.07.10 - Cristian Cojocaru - 2 HP Servers for HPC  2014.07.10 - Cristian Cojocaru - 3 F1 Workload

The Embedded Systems and Mobile Programming track will concentrate on the following subjects:

1. Quadcopter Control - autonomous flying robot
2. Swarm Robotics - design, develop and test of swarm algorithms on existing robots
3. Biometric Electromiograph Hand Control
4. Wireless Sensor Networks - measure and monitor and upload environmental parameters to online repositories
5. Robot Control - program and control an autonomous robot using the posture and gestures of a human operator
6. Multicore Association MCAPI applications on distribute PCs (shared memory) and on PC+FPGA combination (message passing)
7. M-learning (mobile learning): modern learning techniques take advantage of the opportunities offered by mobile technologies; besides mobility, portable devices offer native methods of enabling collaboration and information sharing;
8. Remote Control: learn how the sensing capabilities of your mobile device (accelerometer, compass, touch screen) can provide the means to control a drone and a robotic arm;
9. Games and multimedia: put the hardware capabilities of the mobile device to the test and see what it means to create graphical rich applications.