CS Colloquium

14/03/2019 - 12:00 Information Theory of Deep Learning - The computational benefits of the hidden layers Naftali Tishby Speaker: Naftali Tishby Date : 14/03/2019 - 12:00 Title : Information Theory of Deep Learning - The computational benefits of the hidden layers Abstract: The surprising success of machine learning with deep neural networks poses two fundamental challenges. One is understanding why ... Read more

Unsupervised Learning for Translation across Languages and Images 04/04/2019 - 12:00 Speaker: Yedid Hoshen Seminar: colloquium מיקום: Building 216, Room 201 Abstract: This talk will describe my past and ongoing work on translating images and words between very different datasets without supervision. Although Humans often do not require supervision to make connections between very different ... Read more

Apr. 29th 2019, Sun. 11:00 , Shai Ben David (webpage). University of Waterloo. Location: CS Building (216), Room 201 . Near-optimal Sample Complexity Bounds for Robust Learning of Gaussians Mixtures via Compression Schemes Abstract: We prove that Θ(kd2 /ε^2 ) samples are necessary and sufficient for learning a mixture of k Gaussians in R^d , ... Read more

CS Colloquium talk by Dr. Elad Yom-Tov from Microsoft Research. Title: Online activity as a novel medical diagnostic tool Abstract: The majority of internet users report that they use the web to find information about their medical concerns. Data generated during this search process provides detailed insights into users’ interests and activities at high temporal ... Read more

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

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

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

 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

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

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

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

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

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

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

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

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

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

(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

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