Events Search and Views Navigation

Event Views Navigation

Today

A Theoretical Analysis of Generalization in Graph Convolutional Neural Networks – Ron Levie from Ludwig Maximilian University of Munich

Recording: https://us02web.zoom.us/rec/share/fHCCma3ibcwJDDysXJeiVXwJgIrZB2y6KP70r0lSoVx6f66BFk00LyWd7af-fPpy.RD5WoGdSZW92a31V?startTime=1638093861000 --------------------------------------------------------------------- Hey Everyone, On Sunday 28.11.2021, we will host Ron Levie from Ludwig Maximilian University of Munich. Zoom: https://us02web.zoom.us/j/86540744550?pwd=bTlWMnZSWU1KcHFaSVlaUmR3aDNNUT09 Meeting ID: 865 4074 4550 Passcode: 748585 Title A Theoretical Analysis of Generalization in Graph Convolutional Neural Networks Abstract In recent years, the need to accommodate non-Euclidean structures in data science has brought a ... Read more

Equivariant Subgraph Aggregation Networks – Haggai Maron (NVIDIA Research)

The recording from Haggai's talk: https://us02web.zoom.us/rec/share/jCgJIjXL_UM5KV2z7NwgL3ij2SuLvrTLmVGF4OkI9Vk_J4RFfgYx79h9iC7Z41XQ.3FksbTtcNCIk-phG?startTime=1639303317000 On Sunday 12.12.2021, we will host Haggai Maron from NVIDIA Research. Zoom: https://us02web.zoom.us/j/85743049730?pwd=dVNRcVBJRlJxaTkrZzZkdSt1ajlUQT09 Meeting ID: 857 4304 9730 Passcode: 902259 Title:  Equivariant Subgraph Aggregation Networks Abstract: Message-passing neural networks (MPNNs) are the leading architecture for deep learning on graph-structured data, in large part due to their simplicity and scalability. ... Read more

Generalization in RL – A Bayesian Perspective (Aviv Tamar, Technion)

On Sunday 19.12.2021, we will host Aviv Tamar from Technion. Zoom https://us02web.zoom.us/j/85352616833?pwd=ZDBQNVBESFg2cERlalRhbWNrbzIrQT09 Meeting ID: 853 5261 6833 Passcode: 897342 Title Generalization in RL - A Bayesian Perspective Abstract How can an agent learn to quickly perform well in an unknown task? This is the basic question in reinforcement learning (RL), and is critical for any ... Read more

The implicit bias of SGD: Minima stability analysis – Tomer Michaeli, Technion

The recording of the talk: https://us02web.zoom.us/rec/share/kIED6jkl9xH8y8pzyHAlYig11X11pbDjBqBsijV1kvrzIeOnElEr1ruFhTA1GVLN.vsmhBZvDEjvRx0Kc?startTime=1640513140000 Zoom https://us02web.zoom.us/j/83447514190pwd=cDVsc3Y0dWJOTFIwNlhSQmV5Vkpudz09 Meeting ID: 834 4751 4190 Passcode: 1212 Title The implicit bias of SGD: Minima stability analysis Abstract One of the puzzling phenomena in deep learning, is that neural networks tend to generalize well even when they are highly overparameterized. This stands in sharp contrast to classical wisdom, ... Read more

Learning with fewer labels in Computer Vision – Amir Bar – TAU

The recording of Amir's talk: https://us02web.zoom.us/rec/play/eErrSv8QOE9pC0bNNU4cB46ZiUXuKwbaEXv01MHvyFYTcwikE3Tb4FNob3A00Fi-6csubiImwmcE2OIl.sfukRxaffBiRikPo?startTime=1641117754000 Learning Club BIU - Amir Bar - TAU When Sun, January 2, 2022, 12pm – 1pm Zoom https://us02web.zoom.us/j/83447514190?pwd=cDVsc3Y0dWJOTFIwNlhSQmV5Vkpudz09 Meeting ID: 834 4751 4190 Passcode: 1212 Title: Learning with fewer labels in Computer Vision Abstract: In recent years, deep neural networks have transformed the field of Computer Vision. Current neural ... Read more

Informed Data Science – CS Colloquium talk by Dr. Amir Gilad Duke University (Duke)

Building 403 Room 67

Monday, January 3, 2022 10:00 A.M. יום ב', א' בשבט תשפ"ב בשעה 10:00   Dr. Amir Gilad, Duke University Informed Data Science Data science has become prevalent in various fields that affect day-to-day lives, such as healthcare, banking, and the job market. The process of developing data science applications usually consists of several automatic systems that manipulate ... Read more

Perspectives on Privacy

See following pdf - פרספקטיביות 5.1.22   Link to Zoom - https://us02web.zoom.us/j/85399051733?pwd=UmJJSi9YR3A0a2JrTDlORytLbEQwQT09  

 Learning Club – Itai Lang – TAU – Geometric Adversarial Attacks and Defenses on 3D Point Clouds

Learning Club - Itai Lang - TAU - Geometric Adversarial Attacks and Defenses on 3D Point Clouds When: Sun, January 9, 2022, 12pm – 1pm Title: Geometric Adversarial Attacks and Defenses on 3D Point Clouds Abstract: Deep neural networks are prone to adversarial examples that maliciously alter the network's outcome. Due to the increasing popularity ... Read more

NLP session at AI Week – featuring talks by Prof. Yoav Goldberg and Prof. Ido Dagan

Keynote Yoav Goldberg ,  Research Director of AI2 Israel; Professor at the Computer Science Department, Bar-Ilan University 11:05 - 11:25  Calendar 1  Calendar Beyond End-to-End: the Case of Multi-text Summarization Ido Dagan ,  Professor at the Department of Computer Science, Bar-Ilan University; Director, Bar-Ilan Data Science Institute

MLIS-TCE CONFERENCE – AI: From Hype to Productivity

Join us to the Annual Symposium of MLIS– the Technion AI center and TCE Center, on February 24, 2022, at ELMA Arts Complex . AI is now THE Buzz word, but what are the true current capabilities? What is state-of-the-art and what can be implemented? In this symposium, we differentiate fact from (current) fiction through ... Read more

₪200

Continuous vs. Discrete Optimization of Deep Neural Networks. Nadav Cohen (TAU).

On Sunday 6.3.22 12:00 we will host Nadav Cohen from Tel-Aviv University. Please see the details below. The recording of Nadav' talk: https://us02web.zoom.us/rec/share/cNPxCTCpoLjYZFQI0MMiiukHgNypjRiBkAEobfovvw-ebJzaF1r0RNDpXbfZhdIJ.wmI2PSdk1z3fGxyu?startTime=1646561098000 Title: Continuous vs. Discrete Optimization of Deep Neural Networks Abstract: Existing analyses of optimization in deep learning are either continuous, focusing on variants of gradient flow (GF), or discrete, directly treating variants ... Read more

Learning to Cooperate and Compete in Diplomacy. Dr. Noam Brown, FACEBOOK. (CS Colloquium)

Building 216 room 201

Dr. Noam Brown Will lecture on Learning to Cooperate and Compete in Diplomacy AI has made incredible progress in purely adversarial games such as chess, go, and poker. However, the real world involves a complex mixture of cooperation and competition, sometimes with irrational or suboptimal participants, and in these settings past AI techniques fall apart. For ... Read more

Deep Learning for Representation Learning by Dr. Uri Shaham Yale University (CS Colloquium)

Building 216 room 201

Dr. Uri Shaham. Yale University Will lecture on Deep Learning for Representation Learning In this talk I will present two deep learning-based algorithms for representation learning. In the first half of the talk I will present SpectralNet, a  deep learning approach for spectral clustering, which is scalable and allows for straight-forward out of sample extension.  ... Read more

Learning to Plan in the Real World – Roni Stern, Ben Gurion University

Building 216 room 201

Prof. Roni Stern, Ben Gurion University Learning to Plan in the Real World Planning is often referred to as the art of thinking before acting. As such, automated planning is a long-term goal of Artificial Intelligence (AI). Most planning algorithms in the literature are model-based, in the sense that they assume a compositional model of ... Read more

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators. Rinon Gal (TAU and NVIDIA).

Zoom: https://us02web.zoom.us/j/85784376223?pwd=VkMvdGl1YXFBMExSdC9mRnVnZjZIQT09 Meeting ID: 857 8437 6223 Passcode: 1212 Rinon Gal from Tel-Aviv university and NVIDIA. Title: StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators Abstract: Can a generative model be trained to produce images from a specific domain, guided by a text prompt only, without seeing any image? In other words: can an image generator ... Read more

Robust Android Malware Detection, Harel Berger (Ariel U.)

 The lecture will be given by  Mr. Harel Berger from Ariel University in zoom..   zoom link:  https://us02web.zoom.us/j/83383478356 Title: Robust Android Malware Detection Abstract: A growing number of malware detection methods are heavily based on Machine Learning (ML) and Deep Learning techniques. However, these classifiers are often vulnerable to evasion attacks, in which an adversary manipulates a malicious instance from being detected. This ... Read more

Solving Stochastic Programming Problems by Operator Splitting. Jonathan Eckstein, Rutgers Business School.

Conference Room Building 605, 3rd Fl. Bar-Ilan University

Solving Stochastic Programming Problems by Operator Splitting A B S T R A C T This talk describes the solution of convex optimization problems that include uncertainty modeled by a finite but potentially very large multi-stage scenario tree. In 1991, Rockafellar and Wets proposed the progressive hedging (PH) algorithm to solve such problems. This method ... Read more

Model-Based Deep Learning in Signal Processing and Communications, Dr. Nir Shlezinger (BGU)

Title: Model-Based Deep Learning in Signal Processing and Communications Abstract: Recent years have witnessed a dramatically growing interest in machine learning (ML) methods. These data-driven trainable structures have demonstrated an unprecedented empirical success in various applications, including computer vision and speech processing. The benefits of ML-driven techniques over traditional model-based approaches are twofold: First, ML ... Read more

TAU Style: inversion, editing, and applications of StyleGAN. Dr. Amit Bermano.

Building 216 room 201

Speaker: Dr. Amit Bermano from Tel-Aviv University. Title: TAU Style: inversion, editing, and applications of StyleGAN. Abstract: The generative abilities of GANs are revolutionizing the field of image synthesis and manipulation. Specifically, StyleGAN reaches the highest levels of image quality, and has become the de-facto golden standard for the editing of facial images.  StyleGAN is unsupervised, ... Read more

Computational challenges in protein-RNA interactions, Dr. Yaron Orenstein (BGU)

Building 216 room 201

Dr. Yaron Orenstein Ben-Gurion University Computational challenges in protein-RNA interactions Protein-RNA interactions play vital roles in many cellular processes, and as a result are the main focus of many biological studies. Biologists would like to efficiently measure protein-RNA interactions in high-throughput, and based on these high-throughput experimental measurements train accurate machine-learning models to predict interactions ... Read more

DeepDPM: Deep Clustering With an Unknown Number of Clusters. Meitar Ronen (Ben-Gurion University)

The recording of Meitar's talk is available: https://us02web.zoom.us/rec/share/mdFnT_lf6ct-9VRfTFhnrsEe9724KteEsl7v8I86zf19AaDtKiChgM3Ai6zxQ5CG.PcEfwNZ04_H-NsGm?startTime=1650790948000 ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ On Sunday 24.4.22, at 12:00, we will host Meitar Ronen from Ben-Gurion University. Zoom: https://us02web.zoom.us/j/85784376223?pwd=VkMvdGl1YXFBMExSdC9mRnVnZjZIQT09 Meeting ID: 857 8437 6223 Passcode: 1212 Title: DeepDPM: Deep Clustering With an Unknown Number of Clusters. Abstract: Deep Learning (DL) has shown great promise in the unsupervised task of clustering. ... Read more

Tissue level insights from cellular measurements. Matan Hofree (Weizmann)

Building 216 room 201

Department of Computer Science - Bar-Ilan University Computer Science Colloquium Monday, April 25, 2022 12:00 P.M. Dr. Matan Hofree Weizmann Institute Will lecture on: Tissue level insights from cellular measurements Identifying multi-cellular hubs by co-variation analysis of single-cell expression Therapy response varies considerably among cancer patients and depends on tumor intrinsic factors and interactions with ... Read more

Label-free Domain Adaptation and Multimodal Manifold Learning with Riemannian Geometry. Ronen Talmon (Technion)

The recording of Ronen's talk is available at the following link: https://us02web.zoom.us/rec/share/CyXhXnADPm2gwEPqa4NDasRx3Zz_1DOUMR8LgAiBmO6uPy3JB7ydmXXhorZV55RP.xQTltElplVGiOVcR?startTime=1651395685000 Title: Label-free Domain Adaptation and Multimodal Manifold Learning with Riemannian Geometry Abstract: Recently, Riemannian geometry has become a central ingredient in a broad range of data analysis and learning tools. Broadly, it facilitates features of complex high-dimensional data with a known non-Euclidean geometry. In this ... Read more

הכנס הראשון למחקר מבוסס-נתונים של האינטרנט בישראל

Faculty of Law Building 306, room 200 Faculty of Law Building 306, room 200

Videos from the conference are available here:  https://www.isoc.org.il/event/conference-data-based-internet-research-in-israel When: 10/5/2022, 9-13 What: https://dsi.biu.ac.il/internet-event-2022-agenda Where: Law Building 306 Room 200, Bar-Ilan University    

AI Data Science Summit 2022

Auditorium of the College of Management 2 Elie Wiesel Street Rishon LeTsiyon, Center District 7579806

Prof. Gal Chechik, Director of AI at NVIDIA, Professor at BIU Title: Personalizing Federated learning with hypernetworks Abstract: Federated learning (FL) is the task of learning a model over multiple disjoint local datasets. It is particularly useful when local data cannot be shared due to privacy, storage, or communication constraints. Personalized Federated Learning (PFL) allows each ... Read more

Mechanism Design with Moral Bidders. Dr. Sigal Oren (BGU).

Building 216 room 201

Next week's colloquium will be given by Dr, Sigal Oren from Ben Gurion University. The lecture will be given in Person. Title:  Mechanism Design with Moral Bidders Abstract: A rapidly growing literature on lying in behavioral economics and psychology shows that individuals often do not lie even when lying maximizes their utility. In this work, we attempt to incorporate these findings into ... Read more

Training for Responsible AI 

The Steinhardt Museum of Natural History, TAU

When: Monday May 16, 2022 Where: The Steinhardt Museum of Natural History, TAU Registration (free) is required: Register Training for Responsible AI  co-organized by IDSI Tel Aviv University TAD Community on AI, Ethics & Law and The Chief Justice Shamgar Center for Digital Law and Innovation (pending)     Schedule Outline   08:30 – 09:00 | Registration and light breakfast ... Read more

Better Environments for Better AI. Sarah Keren (Technion)

Building 216 room 201

Title:  Better Environments for Better AI  Abstract: Most AI research focuses exclusively on the AI agent itself, i.e., given some input, what are the improvements to the agent’s reasoning that will yield the best possible output? In my research, I take a novel approach to increasing the capabilities of AI agents via the use of ... Read more

Law and Data Science Collaboration workshop

Faculty of Law Building 306, room 200 Faculty of Law Building 306, room 200, Israel

See details in following pdf file:   שיתוף פעולה מחקרי בין מדע הנתונים ומשפטים C

(R?)evolution Times. Prof. Moshe Tennenholtz (Technion)

Building 216 room 201

Prof. Moshe Tennenholtz, Technion Will lecture on: (R?)evolution Times Recent years have shown dramatic progress in AI. Deep learning approaches employing the so-called "foundational models" are shaking the grounds of technology allowing for innovative products and services at quite an amazing speed. Criticisms and failures of these approaches have been considered: the need to incorporate ... Read more

Party Tricks: On Primaries and Gerrymandering. Omer Lev (BGU)

CS colloquium lecture by Dr. Omer Lev from Ben-Gurion University. Title: Party Tricks: On Primaries and Gerrymandering Abstract: In the last few years, the effects that primaries and gerrymandering have on election outcomes became a commonly debated issue, particularly in the US. Both primaries (candidate selection by parties) and district-based elections are examples of mechanisms that involve adding stages to a decison-making ... Read more

Check invite

This event has a video call. Join: https://meet.google.com/ttt-uona-jmx

Mahmood Sharif Guest Lecture From TAU – Learning Club 12.6.22

###### Meeting Info ###### Title: Toward robust malware detection and faithfully evaluating the robustness of neural networks Abstract: Adversarial examples have emerged as a profound challenge and a critical concern for several application domains, sparking interest in developing adversarially robust machine-learning (ML) models and reliable methods for assessing robustness. In this talk, I will discuss ... Read more

Ofir Lindenbaum Guest Lecture From BIU – Learning Club 19.6.22

The recording of Ofir's talk and slides is available here. ###### Meeting Info ###### Title: Deep learning for tabular biomedical data Abstract: Biomedical datasets are often low-sample-size or high-dimensional. Practitioners in this domain prefer linear or tree-based models over neural networks since the latter are harder to interpret and tend to overfit when applied to tabular ... Read more

Generalization in Deep Learning Through the Lens of Implicit Rank Minimization. Nadav Cohen (TAU).

Building 216 room 201

CS colloquium lecture will be given by Dr. Nadav Cohen from Tel-Aviv University. Title: Generalization in Deep Learning Through the Lens of Implicit Rank Minimization Abstract: Understanding deep learning calls for addressing three fundamental questions: expressiveness, optimization and generalization.  Expressiveness refers to the ability of compactly sized neural networks to represent functions capable of solving real-world ... Read more

BIU learning club – Jack Hessel – The Case for Reasoning Beyond Recognition

Location: Engineering building (1103), room 329 Title:The Case for Reasoning Beyond RecognitionAbstract:Algorithms that can jointly process modalities like images+text are needed for next generation search, accessibility, and robot interaction tools. Simply recognizing objects in images, however, is rarely sufficient; to truly be useful, machines must be capable of deeper commonsense inferences about sophisticated multimodal contexts. I'll ... Read more

BIU learning club – Sivan Sabato – Interactive Learning with Discriminative Feature Feedback

Location: Zoom meeting: https://us02web.zoom.us/j/4685913265Title:Interactive Learning with Discriminative Feature Feedback  Abstract:In this talk I will discuss a model of learning with feature-based explanations, that we call Discriminative Feature Feedback. This model formalizes a natural notion of interactive learning with explanations. We study algorithms for this model, including robust algorithms for adversarial and stochastic settings, and derive insightful new results ... Read more

BIU learning club – Students’ talks

NameLab HeadTitle12:00-12:15Ori ErnstIdo DaganBeyond End-to-End: The Case of Multi Document Summarization12:15-12:30Shon OtmazginYoav GoldbergLingMess & F-COREF: Fast, Accurate, and Easy to Use models for Coreference Resolution12:30-12:45Lior Frenkel Jacob GCalibration of Medical Imaging Classification Systems with Weight Scaling12:45-13:00Coby PensoEthan FetayaFunctional Ensemble Distillation13:00-14:00Lunch

BIU learning club – Amir Globerson – Notions of simplicity in deep learning: From time series to images

Location:Engineering building (1103), room 329Title:Notions of simplicity in deep learning: From time series to images Abstract:It is standard practice indeep learning to train large models on relatively small datasets. This canpotentially lead to severe overfitting, but more often than not, test error isactually good. This phenomenon has prompted research on the so-called "ImplicitBias of Deep Learning Algorithms". ... Read more

High dimensional expanders beyond spectral analysis, Talk by Dudi Mass

on 23.11.22 at 12:00 we will have a festive talk by Dudi Mass, summarizing his PhD., in Building 403, room 217. (this will be part of the theory seminar organized by Arnold Filtser)   ************************************************* **There will be food served in the talk *** ******************************************   Title of talk : High dimensional expanders beyond spectral analysis    Abstract:  In ... Read more

BIU learning club – Tom Tirer – Exploring Deep Neural Collapse via Extended and Controlled Unconstrained Features Models

Location:Engineering building (1103), room 329Title:Exploring Deep Neural Collapse via Extended and Controlled Unconstrained Features ModelsAbstract:Training deep neural networks for classification often includes minimizing the training loss beyond the zero training error point. In this phase of training, a "neural collapse" (NC) behavior has been empirically observed: the variability of features (outputs of the penultimate layer) ... Read more

TAU Style: inversion, editing, and applications of StyleGAN. Dr. Amit Bermano from Tel-Aviv University (CS Colloquium)

Building 216 room 201

(CS Colloquium) TAU Style: inversion, editing, and applications of StyleGAN. Dr. Amit Bermano Tel-Aviv University  Abstract:  The generative abilities of GANs are revolutionizing the field of image synthesis and manipulation. Specifically, StyleGAN reaches the highest levels of image quality, and has become the de-facto golden standard for the editing of facial images. StyleGAN is unsupervised, ... Read more

Recovering Data Semantics. Dr. Roee Shraga (CS Colloquium)

Building 203 Room 221

Sunday, December 4, 2022 11:00 A.M. Building 203 Room 221 Dr. Roee Shraga Northeastern University in Boston י רצ ה על Will lecture on Recovering Data Semantics In data science, it is increasingly the case that the main challenge is finding, curating, and understanding the data that is available to solve a problem at hand. ... Read more

BIU learning club – Chaim Baskin – Graph Representation Learning Through Recoverability

Zoom link: https://us02web.zoom.us/j/4685913265Title:Graph Representation Learning Through Recoverability Abstract:Self-supervised learning methods became popular for graph representation learning because they do not rely on manual labels and offer better generalization. Contrastive methods based on mutual information maximization between augmented instances of the same object are widely used in self-supervised learning of representations. For graph-structured data, however, there are two ... Read more

BIU learning club – Itay Hubara – Toward Fast and Efficient Deep Learning

Zoom link: https://us02web.zoom.us/j/4685913265Title:Toward Fast and Efficient Deep Learning Abstract:Deep Neural Networks (DNNs) are now irreplaceable in various applications. However, DNNs require a vast amount of computational resources. In most cases, complex DNNs training requires several machines working in parallel (most commonly using data parallelism). Moreover, DNNs deployment on devices with limited computational power can be challenging and ... Read more

Genomic language model for function prediction of microbial genes – Danielle Miller (TAU)

בחדר 212 בניין 212

דוקטורנטית מאת״א תבוא להרצות על מודלי שפה לגנומים בקטריאלים. מוזמנים להגיע ולהפיץ לסטודנטים ולחברי סגל נוספים. ההרצאה תתקיים בשעה 14:00 ביום ב׳ 12.12 בחדר 212 בניין 212. כמו כן, אני מתכנן לשדר אותה בזום: https://us02web.zoom.us/j/5509052372 Title:  Genomic language model for function prediction of microbial genes Abstract: Revealing the function of uncharacterized genes is a fundamental challenge in an era of ever-increasing ... Read more

BIU learning club – Ravid Shwartz-Ziv – Exploring the Successes and Limitations of Deep Learning

Location:Engineering building (1103), room 329Title:Exploring the Successes and Limitations of Deep Learning Abstract:In this talk, we will explore the successes and limitations of deep learning networks and highlight the need for more rigorous evaluation. Tree ensemble models often outperform deep learning models for tabular data. However, recently there have been claims that some new deep-learning models ... Read more

The tree reconstruction game: phylogenetic reconstruction using reinforcement learning. Dana Azouri (TAU)

Building 212 Room 212

The tree reconstruction game: phylogenetic reconstruction using reinforcement learning Dana Azouri דוברת: דנה עזורי, דוקטורנטית מאת״א. תתקיים בחדר 212 בניין 212. הרצאה בנושא שחזור עצים פילוגנטיים באמצעות למידת חיזוקים - יום ב׳ 26.12 בשעה 14:00 The following two fields have never interacted before: reinforcement learning and molecular evolution. Here we develop a reinforcement-learning algorithm to ... Read more