WEKA Hands On Workshop

Building 504, room 5

סדנא יישומית לסיווג וניתוח אשכולות Classification & Clustering    יועבר ע"י פרופ' רועי גלברד עבודה בסדנאות תעשה על המחשבים האישיים של המשתתפים. :לנוכח אופיין המיוחד הסדנאות מוגבלות ל30 משתתפים, נא הקדימו והירשמו. http://dsi.biu.ac.il/events/hands_on_tutorial_registration-feb-2018 :מומלץ לצפות בסרטון הבא לפני הסדנא מכון מדע הנתונים: הדגמת שימוש בכלי ניתוח "ידידותיים" - סיווג וניתוח אשכולות, פרופ' רועי גלברד   להורדת  ... Read more

Distilling Relevant Information to Support Human-Human and Human-Agent Collaboration (Ofra Amir, DSI Learning Club)

Gonda Building (901), Room 101

Ofra Amir (Faculty, Technion – Israel Institute of Technology). Distilling relevant information to support human-human and human-agent collaboration Abstract: One of today's biggest challenges is the heightened complexity and information overload stemming from increasingly interacting systems, consisting of both humans and machines. In this talk, I will describe work that aims to address this challenge in ... Read more

Synthesis and Cloning Human Voices (Eliya Nachmani, DSI Learning Club)

Gonda Building (901), Room 101

Mar 22nd, Thu 10:00 , Eliya Nachmani. Tel-Aviv University / Facebook AI Research (PhD Student). Location: Gonda Building (901), Room 101. Synthesis and Cloning Human Voices Abstract: Text to speech (TTS) is able to transform text to speech. In this talk we present a new neural TTS for voices that are sampled in the wild. ... Read more

The Role of Minimal Complexity Functions in Unsupervised Learning of Semantic Mappings (Tomer Galanti, DSI Learning Club)

Gonda Building (901), Room 101

Tomer Galanti (PhD Student, Tel Aviv University) The Role of Minimal Complexity Functions in Unsupervised Learning of Semantic Mappings Abstract: We discuss the feasibility of the following learning problem: given unmatched samples from two domains and nothing else, learn a mapping between the two, which preserves semantics. Due to the lack of paired samples and without ... Read more

Learning Common Sense: a Grand Challenge for Academic AI Research by Oren Etzioni (IEEE student workshop)

Bar-Ilan University, Faculty of Engineering, Hall 02

** Note: This event is canceled! ** Title of talk:  Learning Common Sense: a Grand Challenge for Academic AI Research   Speaker: Prof. Oren Etzioni,  Allen Institute for Artificial Intelligence   Abstract: In a world where Google, Facebook, and others possess massive proprietary data sets, and unprecedented computational power---how is a graduate student to make a dent in ... Read more

DIY Classification & Dear Data Scientist, Label Data or Die (News, Economics and AI meetup)

Thomson-Reuters offices Park Ofer, 94 Derech Em Hamoshavot Oren Building (Building 6), entrance level floor · Petakh Tiqwa Park Ofer, 94 Derech Em Hamoshavot, Petakh Tiqwa, Israel

A News, Economics and AI meetup 18:00-18:30 gathering + pizza 18:30-19:00 "DIY Classification" by Ehud Azikri and Lior Weintraub 19:00-20:15 "Dear Data Scientist, Label Data or Die" by Tal Perry see meetup page for full details: http://meetu.ps/e/Fhrpb/1b3Yc/f

Detecting and Correcting for Label Shift with Black Box Predictors by Zachary Chase Lipton (DSI Learning Club)

Gonda Building (901), Room 101.

June 11th, Mon. 11:00 , Zachary Chase Lipton (webpage). Carnegie Mellon University (CMU). Location: Gonda Building (901), Room 101. Detecting and Correcting for Label Shift with Black Box Predictors Abstract: Faced with distribution shift between training and test set, we wish to detect and quantify the shift, and to correct our classifiers without test set ... Read more

A Provably Correct Algorithm for Deep Learning that Actually Works by Eran Malach (DSI Learning Club)

Gonda Building (901), Room 101.

June 14th, Thu 10:00 , Eran Malach (webpage). The Hebrew University of Jerusalem (PhD Student) Location: Gonda Building (901), Room 101. A Provably Correct Algorithm for Deep Learning that Actually Works Abstract: We describe a layer-by-layer algorithm for training deep convolutional networks, where each step involves gradient updates for a two layer network followed by ... Read more

Tamir Hazan, Technion . “Direct Optimization through argmax for Discrete Variational Auto-Encoder” (DSI Learning Club)

Gonda Building (901), Room 101.

Nov. 25th 2018, Sun. 12:00 , Tamir Hazan (webpage). Technion - Israel Institute of Technology. Location: Gonda Building (901), Room 101. Direct Optimization through argmax for Discrete Variational Auto-Encoder Abstract: Reparameterization of variational auto-encoders is an ehttps://sites.google.com/view/biu-learning-clubffective method for reducing the variance of their gradient estimates. However, when the latent variables are discrete, a reparameterization ... Read more

New Capabilities in Unsupervised Image to Image Translation by Sagie Benaim, TAU (DSI Learning Club talk)

Gonda Building (901), Room 101.

Feb. 24th 2019, Sun. 12:00 , Sagie Benaim (webpage). Tel-Aviv University (PhD Student). Location: Gonda Building (901), Room 101. New Capabilities in Unsupervised Image to Image Translation Abstract: In Unsupervised Image to Image Translation, we are given an unmatched set of images from domain A and domain B, and our task is to generate, given ... Read more

Fundamentals of Deep Learning for Natural Language Processing – NVIDIA DLI full day workshop

building 604, room 202

The NVIDIA Deep Learning Institute (DLI) and The Data Science Institute at Bar-Ilan University invite you to attend a hands-on deep learning workshop on 25-02-2019 from 09:00-17:00 at room 202 Building 604, exclusively for verifiable academic students, staff, and researchers. NVIDIA DLI offers hands-on training for developers, data scientists, and researchers looking to solve challenging ... Read more

Using information theory for deep learning, Raja Giryes (TAU)

Nano Building (206), Room B991

Apr. 28th 2019, Sun. 12:00 , Raja Giryes (webpage). Tel-Aviv University. Location: Nano Building (206), Room B991. Using information theory for deep learning Abstract: In this talk, we will use two tools in information theory to gain a better understanding of deep learning training. First, we will describe the problem of analog channel coding and ... Read more

Hacking Classifiers – talk by Ran Gilad-Bachrach (TAU)

Gonda Building (901), Room 101

Ran Gilad-Bachrach from Tel-Aviv University. Location: Gonda building (901), room 101. Time: Sunday 10/11 12:00. Hacking Classifiers Abstract: In this talk will explore ways to stretch classifiers and use them in ways they were not intended to be used. In the first part of the talk we will break the training process of classifiers into ... 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

Prof. Gal Chechik Bar-Ilan University: Learning with visual foundation models for Gen AI

CS Auditorium (Bldg. 503)

On May 23,  Prof. Gal Chechik Bar-Ilan University will give a lecture on: Learning with visual foundation models for Gen AI Abstract: Between training and inference, lies a growing class of AI problems that involve fast optimization of a pre-trained model for a specific inference task. These are not pure “feed-forward” inference problems applied to ... Read more