May. 12th 2019, Sun. 12:00 , Lihi Zelnik-Manor and Asaf Noy (webpage). Technion - Israel Institute of Technology and Alibaba. Location: Nano Building (206), Room B991. AutoML by Alibaba: Architecture Search, Anneal and Prune Abstract: Manual network architecture search and hyper-parameter tuning of neural network based algorithms could be a very interesting task but also ... Read more

June. 2nd 2019, Sun. 12:00 , Oren Freifeld (webpage). Ben-Gurion University. Location: Nano Building (206), Room B991. Geometric transformations in deep learning and Bayesian nonparamteric mixture models. Abstract: This talk will focus on two of the main research directions at our Vision, Inference, and Learning group: 1) Geometric transformations in deep learning and 2) Bayesian ... Read more

Yuval from NVIDIA will be giving a tutorial on containers, docker containers, NGC containers, how to use them, etc. - relvant to both novice users and advanced users.

For details and registration: https://sites.google.com/datalab.cs.biu.ac.il/biusummerschool/home?authuser=4

For details and registration: https://sites.google.com/datalab.cs.biu.ac.il/biusummerschool/home?authuser=4

Title: Polynomial-time algorithms are not always welcome – sparse PCA as a case study When: October 27, Sunday, 12:00 Where: Gonda building, room 101 Abstract: The taxing computational effort that is involved in solving some high-dimensional statistical problems, in particular problems involving non-convex optimization, has popularized the development and analysis of  algorithms that run efficiently (polynomial-time) but ... Read more

במסגרת שיתוף הפעולה בין מחב"א לחברת AWS, אני שמח להזמין אתכם ליום עיון בנושא שירותי מחקר בענן. האירוע מיועד לחוקרים, מרצים ועוזרי מחקר המבצעים כיום פעילות מחקר בענן או שוקלים לבצע מחקר בעתיד באמצעות שירותי ענן. מטרת האירוע לתת לחוקרים את הכלים להתמקד במחקר בצורה יעילה. האירוע יתקיים ב-17.11.2019 באוניברסיטה בר-אילן, הפקולטה למדעי החיים, בנין 212, קומה 2, ... Read more

Title: Heuristic learning on the border between success and failure Abstract: Many popular hypothesis classes, such as neural-networks or decision trees, are computationally hard to learn. In practice, however, heuristic algorithms are used to learn these classes with remarkable success. To better understand this gap, we explore probabilistic models where a small change in the ... Read more

Nadav Cohen from TAU Location: Gonda building (901), room 102. Time: Sunday Nov 24th, 12:00 AM -- 13:00 AM. Title: Analyzing Optimization and Generalization in Deep Learning via Trajectories of Gradient Descent Abstract: Understanding deep learning calls for addressing the questions of: (i) optimization --- the effectiveness of simple gradient-based algorithms in solving neural network ... Read more

Special seminar on urban networks by Prof. Gourab Ghoshal from University of Rochester, NY: Gourab will be around from Nov. 25 - 28. If you are interested in meeting with him, please let me know. Please feel free to forward to all relevant groups, peers. PosterGhoshal  

Title: Second-order Optimization Made Practical Abstract: Optimization in machine learning, both theoretical and applied, is presently dominated by first-order gradient methods such as stochastic gradient descent.  Higher-order (preconditioned) optimization methods have become far less prevalent, despite compelling theoretical properties, due to their impractical computation, memory and communication costs.  I will present some recent theoretical, algorithmic ... Read more

Open for all biu students interested to learn how to best utilize the available GPU hardware. Wednesday, December 4⋅10:00am – 12:00pm חדר ישיבות 329, הנדסה Please download following materials before session: profilingTutorial Add to calendar: https://calendar.google.com/event?action=TEMPLATE&tmeid=NGNjb2s0azl0OG9qMmdpZjl2Z3Q5cmZzOWQgb3Jlbi5nbGlja21hbkBt&tmsrc=oren.glickman%40gmail.com Post Event Materials: Talk:  https://www.youtube.com/watch?v=m5He_FlhcRo&feature=youtu.be&t=1 Deck:  https://raanan.blob.core.windows.net/biu/A%20Practical%20Guide%20for%20Reducing%20DNN%20Training%20Time%E2%80%8B.pptx?sp=r&st=2019-12-08T12:50:55Z&se=2020-03-18T20:50:55Z&spr=https&sv=2019-02-02&sr=b&sig=6YtI4y5mhfDK3A9zvpuTd3vLMpyNgITRyouHbz9Hhgs%3D Blog Post: https://sagivtech.com/2017/09/19/optimizing-pytorch-training-code/

Title: GANs for Real-Life Video Applications. Abstract: This talk will focus on two research papers that demonstrate the use of generative adversarial networks for real-life video applications, through face and full-body synthesis. The first paper (“Live Face De-Identification in Video”), proposes a novel method for face de-identification, that enables fully automatic video modification at high ... Read more

Speaker: ALON GONEN Date : 19/12/2019 - 12:00 Title : Beyond Worst Case In Machine Learning: The Oracle Model Abstract: In recent years there has been an increasing gap between the success of machine learning algorithms and our ability to explain their success theoretically. Namely, many of the problems that are solved to a satisfactory degree of precision ... Read more

Sanjeev Khudanpur from John-Hopkins University Two Ideas for Improving Automatic Speech Recognition: One Elegant, and One Very Useful! The Kaldi tools for automatic speech recognition (ASR) are being widely used both for research and for large-scale deployments.  Many innovations large and small have gone into keeping Kaldi up-to-date in this fact-moving field.  I will describe how two ... Read more

Sunday (19.1.20 12:00) we will host Idan Szpektor from Google. The talk will take place at Gonda (building 901) room 101. Title: Dynamic Composition in Conversational Domain Exploration In this talk I will introduce conversational domain exploration, where the user’s goal is to enrich her knowledge of a given domain by conversing with an informative bot.  Such ... Read more

Shauli Ravfogel Title: Unsupervised Distillation of Syntactic Information From Contextualized Neural Representation. Abstract: Contextualized word representations, such as ELMo and BERT, were shown to perform well on a various of semantic and structural (syntactic) task. In this work, we tackle the task of unsupervised disentanglement between semantics and structure in neural language representations: we aim to ... Read more

Part of The Israel Statistical Association workshop: Explainable AI (XAI) workshop Title: Explaining visual understanding: Learn to reason about the perceived world. Speaker: Prof. Gal Chechik Abstract: AI aims to build systems that can interact with their environment, with people and with other agents in the real world. This vision poses hard algorithmic challenges for ... Read more

Talk at AI For Human Languages (free student tickets available for biu students - talk to Reut) Title: What's wrong with Hebrew NLP? And How to Make it Right Speaker: Prof. Reut Tsarfaty The ability to automatically process massive volumes of unstructured texts and turn them into structured information is key to many success stories ... Read more

Title: Differentially Private Ordinary Least Squares Abstract: Linear regression is one of the most prevalent techniques in machine learning; however, it is also common to use linear regression for its explanatory capabilities rather than label prediction. Ordinary Least Squares (OLS) is often used in statistics to establish a correlation between an attribute (e.g. gender) and ... Read more

Amit Somech from tell Aviv University. The lecture will be given in zoom zoom link: https://zoom.us/j4595130079 Thursday noon 12:00 Title: Learning-Based Methods for Automating Exploratory Data Analysis Abstract: Exploratory Data Analysis (EDA) is an integral part of the data-science pipeline, in which users interactively explore datasets by issuing a sequence of analysis operations (e.g. filter, aggregation, and visualization). ... Read more

Academic Webinar, Wednesday, June 10, at 12 pm EST (7 pm Israel time) “No Exit? Three International Experts’ Mathematical Models on Lifting the Lockdown” Dr. Baruch Barzel, Director of BIU’s Complex Network Dynamics Laboratory, will join two other renowned authorities on an academic webinar – “No Exit? Three International Experts’ Mathematical Models on Lifting the ... Read more

On Sunday 21.6 12:00 we will host Daniel Soudry from the Technion in our machine learning seminar. The talk will be about new findings in training deep neural networks, from a number of recent publications by Daniel’s group (see more details below). Due to the coronavirus the talk will take place via zoom: https://zoom.us/j/8461826978 See you ... Read more

On Sunday 26.1 12:00 we will host Ethan Fetaya. Ethan will present his ICML best paper on Symmetries and Universality (joint work with Haggai Maron, Or Litany and Gal Chechik). See paper here, and further details below. The talk will take place over zoom like last time. Zoom link: https://zoom.us/j/99197317021 See you all soon, Felix — Title: "Symmetries and ... Read more

We are excited to announce the first Israeli workshop on geometric deep learning (iGDL) that will take place on August 2nd, 2020 2 PM-6 PM (Israel timezone). The workshop will be in English, and will take place virtually via Zoom due to COVID19 restrictions. For registration and details - https://gdl-israel.github.io/  

The recording of Tomer’s presentation is available in this link.  Title: On the Modularity and Optimization Dynamics of Hypernetworks. Abstract: Hypernetworks are architectures that produce the weights of a task-specific implicit network. A notable application of hypernetworks in the recent literature involves implicit neural representations. In these scenarios, the hypernetwork learns a representation corresponding to ... Read more

Karen Livescu from TTIC Location: Gonda building (901), room 102. Time: Sunday Dec 22th, 12:00 AM -- 13:00 AM. Title: Embeddings for spoken words Abstract: Word embeddings have become a ubiquitous tool in natural language processing. These embeddings represent the meanings of written words. On the other hand, for spoken language it may be more ... Read more

Gilad Yehudai from Weizmann Institute of Science Time: Sunday Jan 10th, 2021 12:00 PM — 13:00 PM. Title: On Size Generalization in Graph Neural Networks and Lottery Tickets Abstract: In this talk, I will survey two recent works, both have results related to the expressivity of neural networks, but in different architectures: On size generalization ... Read more

On Monday, January 11, 21 at 2:45 PM, Dr. Eldar Haber from the Faculty of Law at the University of Haifa will present his article: Eldar Haber, The Wiretapping of Things, 50 UC. D. L. Rev. 733 (2019). The zoom link for the talk is: https://us02web.zoom.us/j/87619539915. Details: Keren Yalin-Mor keren.yalin-mor@biu.ac.il

On Monday, January 18, 21 at 3:00 PM, Dr. Karni Shagel-Peppcorn from the University of Ottawa will present her paper: Karni Chagal-Feferkorn, Am I an Algorithm or a Product? When Products Liability Should Apply to Algorithmic Decision-Makers, 30 Stan. L. & Pol'y Rev. 61 (2019). The zoom link for the talk is: https://us02web.zoom.us/j/87619539915. Details: Keren Yalin-Mor ... Read more

Containers101: Containers, Docker, Kubernetes When: Tue 26/1/2020 14:00-16:00 (Zoom). Details: http://dsi.biu.ac.il/student-position-for-research-project-on-bots-in-social-networks/ Registration: https://forms.gle/aNBiqc1dG1XshLp3A

New methods to understand and generate visual scenes with novel combinations and complex interactions. https://aiweekonline.b2b-wizard.com/expo/agenda

When: 9/3/2020 10:00-12:00 Agenda: 10-10:30: Liron Friend, Developer Relations; Brief intro to Nvidia Nvidia’s Ambassador program for researchers Nvidia NGC: Nvidia docker containers, pretrained models and SDK’s 10:30 – 11:15: Gal Malca, Solution Architect Training neural networks with multi GPU training AMP – training with mixed precision Nvidia SMI and NSight with performance demo NGC ... Read more

Title: Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization Abstract: Direct loss minimization is a popular approach for learning predictors over structured label spaces. This approach is computationally appealing as it replaces integration with optimization and allows to propagate gradients in a deep net using loss-perturbed prediction. Recently, this technique was extended to generative ... Read more