Colloquia and SeminarsTo join the email distribution list of the cs colloquia, please visit the list subscription page.
Computer Science events calendar in HTTP ICS format for of Google calendars, and for Outlook.
Academic Calendar at Technion site.
- Bioinformatics Forum
- BizTEC Forum
- CGGC Weekly Seminar
- Coding Theory Seminar
- Haifux, Haifa Linux Club
- Pixel Club
- Theory Seminar
Upcoming Colloquia & Seminars
TODAY! The Finals - 2016-17 Amdocs Best Project Contest
- Tuesday, 28.3.2017, 16:30
- CS Taub Auditorium 2
You are invited to the final stage of the 2016-17 Amdocs Best Project Contest. The competing teams will present and talk about their projects.
The event will take place on Tuesday, March 28, 2015, 16:30-18:30, in Auditorium 2, CS Taub Building.
You are all invited to cheer, support and be exposed to outstanding projects.
TCE Special Guest Lecture: Revisiting Virtual Caches
- Guri Sohi (University of Wisconsin-Madison)
- Wednesday, 29.3.2017, 11:30
- EE Meyer Building 861
Virtual caches have been around for several decades. They have several advantages in performance and energy efficiency, but have not been used in ubiquitous commercial designs because of problems due to synonyms. To revisit the problem and come up with a practical design, we start with a study of the temporal behavior characteristics of synonyms in several benchmark programs. Exploiting these characteristics we propose a practical virtual cache design with dynamic synonym remapping (VC-DSR) and then evaluate the effectiveness in a CPU context. We also study the application and effectiveness of virtual caches in a GPU context. In this talk we will present the empirical observations than underlie the proposal for VC-DSR, present the design and its effectiveness in a general CPU context. We also present a design to use virtual caches (both L1 and L2) in an integrated GPU context and show how it can significantly reduce the overheads of address translation.
Guri Sohi has been a faculty member at the University of Wisconsin-Madison since 1985 where he currently a John P. Morgridge Professor and a Vilas Research Professor. Sohi's research has been in the design of high-performance microprocessors and computer systems. Results from his research can be found in almost every high-end microprocessor in the market today. He has received the 1999 ACM SIGARCH Maurice Wilkes award, the 2011 ACM/IEEE Eckert-Mauchly Award, and the 2016 IEEE B. Ramakrishna Rau Award. At the University of Wisconsin he was selected as a Vilas Associate in 1997, awarded a WARF Kellett Mid-Career Faculty Researcher award in 2000, a WARF Named Professor in 2007, and a Vilas Research Professor in 2015. He is a Fellow of both the ACM and the IEEE and is a member of the National Academy of Engineering
Pixel Club: Unsupervised Cross-Domain Image Generation
- Adam Polyak (Facebook)
- Wednesday, 29.3.2017, 11:30
- EE Meyer Building 1061
We study the problem of transferring a sample in one domain to an analog sample in another domain. Given two related domains, S and T, we would like to learn a generative function G that maps an input sample from S to the domain T, such that the output of a given function f, which accepts inputs in either domains, would remain unchanged. Other than the function f, the training data is unsupervised and consist of a set of samples from each domain. The Domain Transfer Network (DTN) we present employs a compound loss function that includes a multiclass GAN loss, an f-constancy component, and a regularizing component that encourages G to map samples from T to themselves. We apply our method to visual domains including digits and face images and demonstrate its ability to generate convincing novel images of previously unseen entities, while preserving their identity.
Adam Polyak is a research engineer at Facebook AI Research(FAIR) in Facebook Tel-Aviv, where he works on developing and understanding systems with human level intelligence. Before joining FAIR, Adam completed his M.Sc in computer science at Tel-Aviv University, under the supervision of Prof. Lior Wolf. His thesis focused on methods to accelerate and compress neural networks to allow their deployment on devices with limited computational power.
Theory Seminar: Random High-dimensional Combinatorial Objects
- Nathan Linial (Hebrew University of Jerusalem)
- Wednesday, 29.3.2017, 12:30
- Room 337 Taub Bld.
This is part of our ongoing effort to develop the field of high-dimensional combinatorics. The probabilistic method and the properties of random graphs, random trees, random permutations etc. play a central role in modern combinatorics. In this talk I will discuss some of our findings concerning the higher-dimensional counterparts of these objects.
My collaborators in these investigations are Zur Luria, Maya Dotan, and Michael Simkin
Startup Day and Recruitment at CS
- Wednesday, 29.3.2017, 12:30
- CS Taub Lobby
CS invites you to a STARTUP DAY and recruitment by the presenting firms:
Augury, Axxana, CNOGA, Colu, Driveway, ENSILO, JFrog, Lightbits, SCIO, Sesame, Tabbola, Yotpo.
In addition, lectures will be given by the firms representatives and entrepreneurs .
The event will take place on Wednesday, March 29, 2017 between 12:30-14:30 at the CS Taub Lobby.
More details in the attached documents.
You are all welcome!
Pixel Club: Analysis of Non-Rigid 3D Shapes
- Zorah Lähnerand & Matthias Vestner (TU Munich)
- Wednesday, 29.3.2017, 14:30
- Room 337 Taub Bld.
Zorah Lähner and Matthias Vestner are PhD students from the group of Daniel Cremers at TU Munich. Both are working in the Analysis of Non-Rigid 3D Shapes and in particular consider the (dense) correspondence problem between instances of those. Z.L. will present (an extended version of) her CVPR 2016 paper "Efficient Globally Optimal 2D-to-3D Deformable Shape Matching" (2D-3D), M.V. will present (an extended version of) his CVPR 2017 paper "Product Manifold Filter: Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Space" (PMF).
Abstract Product Manifold Filter:
Finding a dense correspondence between two Non-Rigid shapes is still an open problem. Most existing approaches either make restrictive assumptions on the considered shapes (such as isometry) and/or produce matchings that are neither surjective nor continuous as they rely on some type of nearest neighbor search in a descriptor space - in case of functional maps those descriptors are eg. aligned harmonics. I will present an iterative method that guarantees bijections with increasing continuity at each iteration without any isometry assumptions. If you have already attended a presentation about the PMF, (or even read the paper) you will still see something new: Extension to settings where the optimal solution is not a bijection (partiality, different sampling). Relation of the PMF to quadratic assignment problems (such as discretizations of Gromov-Wasserstein distances).
Finding correspondences between different dimensional objects casts many additional problems. Common descriptors only work on the same dimension and even defining the optimal solution is not always trivial. This setting can, for example, be used to search large collections of 3D shapes based on sketches given by a user. In this talk I will present a method to find correspondences between a 2D silhouette of an object represented by a closed curve - possibly drawn by a human - and a 3D shape. I show retrieval results on a collection of shapes in which both of the inputs are allowed to undergo non-rigid pose deformations. The obtained correspondences are continuous and can be chosen to be either globally optimal or an epsilon-approximation of it (with similar retrieval rates but improved runtime). The talk will include descriptors which are comparable between 2D and 3D but can still handle non-rigid deformations.
Setting Zigzag Straight - An erasure coding scheme and its evaluation in the cloud
- Matan Liram, M.Sc. Thesis Seminar
- Thursday, 30.3.2017, 11:00
- Taub 601
- Prof. E. Yaakobi, G. Yadgar, Prof. A. Schuster
Erasure codes protect data in large scale data centers against multiple concurrent failures. However, in the frequent case of a single node failure, the amount of data that must be read for recovery can be an order of magnitude larger than the amount of data lost. Some existing codes successfully reduce these recovery costs but increase the storage overhead considerably. Others, which are theoretically optimal, minimize the amount of data required for recovery, but incur irregular I/O patterns that may actually increase overall recovery time and cost. Thus, while the theoretical results in this context continue to improve, many of them are inapplicable to realistic system settings, and their benefit remains theoretical as well. This gap between theory and practice has been observed in previous studies that applied theoretically optimal techniques to real systems. In this paper, we present a novel system-level approach to bridging this gap in the context of reducing recovery costs. We optimize the sequentiality of the data read, at the cost of a minor increase in its amount. We use Zigzag, a family of erasure codes with minimal overhead and optimal recovery, and trade its theoretical optimality for real performance gains. Our implementation of Zigzag and its optimizations in Ceph reduces recovery costs with two, three and four parity nodes, for large and small objects alike. We were able to cut down recovery time by up to 20% compared to that of Reed-Solomon, and to reduce the amount of data read and transferred by 18% to 37%.
Pixel Club: Coresets for Kinematic Data: From Theorems to Autonomous Toy-Drones
- Dan Feldman (Haifa University)
- Tuesday, 4.4.2017, 11:00
- EE Meyer Building 1061
A coreset (or core-set) of a dataset is its semantic compression with respect to a set of queries, such that querying the (small) coreset provably yields an approximate answer to querying the original (full) dataset. However, we are not aware of real-time systems that compute coresets in a rate of dozens of frames per second. I will suggest a framework to turn theorems to such systems using coresets. This is by maintaining such a coreset for kinematic (moving) set of n points, and run algorithms on the small coresets, instead of the n points, in real time using weak devices. This also enabled my group to implement a low-cost (< $100) mini-computer with a wireless system that tracks a toy (and harmless) quadcopter which guides guests to a desired room in our department with no help of additional human or remote controller. I will present the system, the sketch of the proofs, as well as extensive experimental results.
* A joint work with Soliman Nasser and Ibrahim Jubran
Dan Feldman is a faculty member and the head of the new Robotics & Big Data Labs in the University of Haifa, after returning from a 3 years post-doc at the robotics lab of MIT. During his PhD in the University of Tel-Aviv he developed data reduction techniques known as core-sets, based on computational geometry. Since his post-docs at Caltech and MIT, Dan's coresets are applied for main problems in Machine Learning, Big Data, computer vision, EEG and robotics. His group in Haifa continues to design and implement core-sets with provable guarantees for such real-time
Modularity, classification and networks in analysis of big biomedical data
- Ron Shamir - COLLOQUIUM LECTURE
- Tuesday, 4.4.2017, 14:30
- Room 337 Taub Bld.
Supervised and unsupervised methods have been used extensively to analyze genomics data, with mixed results. On one hand, new insights have led to new biological findings. On the other hand, analysis results were often not robust. Here we take a look at several such challenges from the perspectives of networks and big data. Specifically, we ask if and how the added information from a biological network helps in these challenges. We show both examples where the network added information is invaluable, and others where it is questionable. We also show that by collectively analyzing omic data across multiple studies of many diseases, robustness greatly improves. Short Bio: ========= Prof. Ron Shamir leads the Computational Genomics group at the Blavatnik School of Computer Science, Tel Aviv University (TAU). He is the founder and head of the Edmond J. Safra Center for Bioinformatics at TAU and holds the Raymond and Beverly Sackler Chair in Bioinformatics. He develops algorithmic methods in Bioinformatics and Systems Biology. His research interests include gene expression analysis, molecular networks, gene regulation and cancer genomics. Methods and software tools developed by Shamir's group are in use by hundreds of laboratories around the world. Shamir received a BSc in Mathematics and Physics from the Hebrew University, and a PhD in Operations Research from UC Berkeley in 1984. He is on the faculty of TAU since 1987. He has published some 270 scientific works, including 17 books and edited volumes, and has supervised more than 50 graduate students. He is on the editorial board of eleven scientific journals and series, and was on the steering committee of RECOMB. He co-founded the Israeli Society of Bioinformatics and Computational Biology, and was society president in 2004-2006. He is a recipient of the 2011 Landau Prize in Bioinformatics, and a Fellow of the ISCB and the ACM. ======================================= Refreshments will be served from 14:15 Lecture starts at 14:30
Pixel Club: Shape Reconstruction:From Axiomatic Coded Light to Learning Stereo
- Ron Slossberg (CS,Technnion)
- Wednesday, 5.4.2017, 11:00
- Room 337 Taub Bld.
1. Freehand Laser Scanning Using Mobile Phone
3D scanners are growing in their popularity as many new applications and products are becoming a commodity. These applications are often tethered to a computer and/or require expensive and specialized hardware. In this chapter of the thesis we demonstrate that it is possible to achieve good 3D reconstruction on a mobile device. We describe a novel approach for mobile phone scanning which utilizes a smart-phone and cheap laser pointer with a cylindrical lens which produces a line pattern attached to the phone using a 3D printed adapter. Non-linear multi-scale line filtering is used to detect the center of the projected laser beam in each frame with sub-pixel accuracy. The line location coupled with the estimated phone position and orientation in 3D space, obtained from publicly available SLAM libraries and marker tracking, permits us to perform a 3D reconstruction of a point cloud of the observed objects. Color and texture are extracted for every point along the scanned line point by projecting the reconstructed points back onto previous keyf-ramed images. We validate the proposed method by comparing the reconstruction error to the ground truth obtained from an industrial laser scanner.
2. Deep Stereo Matching with Dense CRF Priors
Stereo reconstruction from rectified images has recently been revisited within the context of deep learning. Using a deep Convolutional Neural Network to obtain patch-wise matching cost volumes has resulted in state of the art stereo reconstruction on classic datasets like Middlebury and Kitti. By introducing this cost into a classical stereo pipeline, the final results are improved dramatically over non-learning based cost models. However, these pipelines typically include hand engineered post processing steps to effectively regularize and clean the result. Here, we show that it is possible to take a more holistic approach by training a fully end-to-end network which directly includes regularization in the form of a densely connected CRF that acts as a prior on inter-pixel interactions. We demonstrate that our approach applied to both synthetic and real world datasets outperforms an alternative end-to-end network and compares favorably to less holistic
* Supervised by Professor Ron Kimmel
CS Guest Lecture: Doing Stuff with LSTMs
- Yoav Goldberg (Bar-Ilan University)
- Thursday, 6.4.2017, 10:30
- Taub 601
The premise of the talk is processing natural language using machine learning techniques.
While deep learning methods in Natural Language Processing are arguably overhyped, recurrent neural networks (RNNs), and in particular LSTM networks, emerge as very capable learners for sequential data. Thus, my group started using them everywhere. After briefly explaining what they are and why they are cool, I will describe some recent work in which we use LSTMs as a building block.
Depending on my mood (and considering audience requests via email before the talk), I will discuss some of the following: learning a shared representation in a multi-task setting; learning to disambiguate English prepositions using multi-lingual data; learning feature representations for syntactic parsing; representing trees as vectors; learning to disambiguate coordinating conjunctions; learning morphological inflections; and learning to detect hypernyms in a large corpus. All of these achieve state of the art results. Other potential topics include work in which we try to shed some light on what's being captured by LSTM-based sentence representations, as well as the ability of LSTMs to learn hierarchical structures
''Blind'' Visual Inference
- Michal Irani - COLLOQUIUM LECTURE
- Tuesday, 25.4.2017, 14:30
- Room 337 Taub Bld.
In this talk I will show how ''blind'' visual inference can be performed by exploiting the internal redundancy inside a single visual datum (whether an image or a video). The strong recurrence of patches inside a single image/video provides a powerful data-specific prior for solving complex tasks in a ''blind'' manner. The term ''blind'' here is used with a double meaning: (i) Blind in the sense that we can make sophisticated inferences about things we have never seen before, in a totally unsupervised way, with no prior examples or training data; and (ii) Blind in the sense that we can solve complex Inverse-Problems, even when the forward degradation model is unknown. I will show the power of this approach through a variety of example problems (as time permits), including: 1. "Blind Optics" -- recover optical properties of the unknown sensor, or optical properties of the unknown environment. This in turn gives rise to Blind-Deblurrimg, Blind Super-Resolution, and Blind-Dehazing. 2. Segmentation of unconstrained videos and images. 3. Detection of complex objects and actions (with no prior examples or training). Short Bio: ========== Michal Irani is a Professor at the Weizmann Institute of Science, in the Department of Computer Science and Applied Mathematics. She received a B.Sc. degree in Mathematics and Computer Science from the Hebrew University of Jerusalem, and M.Sc. and Ph.D. degrees in Computer Science from the same institution. During 1993-1996 she was a member of the Vision Technologies Laboratory at the Sarnoff Research Center (Princeton). She joined the Weizmann Institute in 1997. Michal's research interests center around computer vision, image processing, and video information analysis. Michal's prizes and honors include the David Sarnoff Research Center Technical Achievement Award (1994), the Yigal Allon three-year Fellowship for Outstanding Young Scientists (1998), the Morris L. Levinson Prize in Mathematics (2003), and the Maria Petrou Prize (awarded by the IAPR) for outstanding contributions to the fields of Computer Vision and Pattern Recognition (2016). She received the ECCV Best Paper Award in 2000 and in 2002, and was awarded the Honorable Mention for the Marr Prize in 2001 and in 2005. ====================================== Refreshments will be served from 14:15 Lecture starts at 14:30
Open Day For Graduate Studies At Technion Computer Science and Electrical Engineering
- Wednesday, 26.4.2017, 10:30
- Room 337 Taub Bld.
The 2016 open day invite outstanding undergraduates from all universities to come to the Technion and learn about the faculties of Computer Science and Electrical Engineering, meet faculty and graduate students and hear a fascinating talk by Prof. Lior Kornblum: "How to Connect Exotic Physics with Future Devices" and by Oded Cohen, VP in IBM Haifa: "Do Advanced Degrees Indeed Advance?"
The event will be held on Wednesday, April 26 2017, between 10:30-16:00, in EE Meyer Bulding, Room 815 (8th floor). and in CS Taub Building, room 337 (3rd floor).
The program will include review on curriculum and admission requirements in each of the faculties, as well as scientific lectures. In addition, personal meeting between candidates and vice deans of both faculties will be optional.
It is recommended that you bring along your first degree grades chart.
Attendance at the open day requires pre-registration.
More details and program.
CGGC Seminar: Geometric Methods for Realistic Animation of Faces
- Amit Bermano (Princeton Graphics Group)
- Sunday, 30.4.2017, 13:30
- Room 337 Taub Bld.
In this talk, I will briefly introduce myself, mainly focusing on my doctoral dissertation, addressing realistic facial animation.
Realistic facial synthesis is one of the most fundamental problems in computer graphics, and is desired in a wide variety of fields, such as film and advertising, computer games, teleconferencing, user-interface agents and avatars, and facial surgery planning.
In the dissertation, we present the most commonly practiced facial content creation process, and contribute to the quality of each of its three steps.
The proposed algorithms significantly increase the level of realism attained and therefore substantially reduce the amount of manual labor required for production quality facial content.
TCE Workshop: 2017 Stephen and Sharon Seiden Frontiers in Engineering and Science
- Friday, 5.5.2017, 09:30
- TCE, TECHNION
You are invited to the upcoming 2017 Stephen and Sharon Seiden Frontiers in Engineering and Science Workshop. This year, the workshop will be titled "Beyond CMOS: From Devices to Systems" and will be held at the Technion, Haifa, Israel on Monday-Tuesday, June 5-6, 2017.
This workshop will bring together researchers and leaders from academia and industry to discuss the many different aspects of emerging solid state memories including device physics, circuits, architecture, reliability, security, and systems. These technologies include RRAM, PCM, 3D Xpoint, STT MRAM, CBRAM, memristors, and many others from all of these fields, including executives from industry who will discuss the commercialization aspects of these technologies.
A call for posters will follow soon, as well as the final program. Registration opens on March 15th, 2017.
More details will be available on the workshop website.