Learning algorithms have been an important cornerstone in numerous modern application domains, and are a key ingredient in many technological eco-systems. Examples include A/B testing,  recommender system design, pricing analytics, trade execution algorithms, and online health monitoring, to name but a few. Many such algorithms are deployed and run at massive scale and are part and parcel of the AI revolution we are all witnessing.  The academic literature, from which many of these algorithms and ideas originate, has mostly focused on what can be referred to as “stationary” environments, where ambient operating parameters and conditions remain stable. This is rarely the case in many real-world settings. In this talk we will illustrate some design principles that allow classical online learning approaches to be adapted to changing environments.  The ideas will be illustrated in a simple stylized setting (albeit one that has been widely adopted in the tech sector) but are applicable more broadly. 

Assaf Zeevi is Professor and holder of the Kravis chair at the Graduate School of Business and the Data Science Institute, Columbia University. His research and teaching interests lie at the intersection of Operations Research, Statistics, and Machine Learning. In particular, he has been developing theory and algorithms for reinforcement learning, Bandit problems, stochastic optimization, statistical learning and stochastic networks. Assaf is a member of several scientific advisory boards for startup companies in the high technology sector.  His work has found applications in online retail, healthcare analytics, dynamic pricing, recommender systems, and online marketplaces. Assaf received his B.Sc. and M.Sc. (Cum Laude) from the Technion, in Israel, and subsequently his Ph.D. from Stanford University in 2001. He has held visiting positions at Stanford University, the Technion and Tel Aviv University. 

Detection and spectro-temporal localization of communication transmissions are crucial for tasks related to understanding, managing, and protecting the RF spectrum. Achieving this goal for wideband spectrum in real-time is a challenging problem. Existing methods are not capable of detecting multiple RF emissions in real-life scenarios, where the spectrum is heavily occupied. Here, we will present the problem, discuss the main challenges, overview solutions available in the open literature, and suggest other solutions based on our own experience.

Anat Hershko joined Elbit Systems - EW & SIGINIT - Elisra in 2019 as an Algorithm Engineer in the field of communication signals. In Elbit, Anat works on AI-based algorithms for detecting and classifying communication signals. During her career, Anat gained extensive experience with wireless and optical systems and PHY layer full cycle modem design. Anat holds a BSC degree in Electrical Engineering from Tel Aviv University.

Direction of arrival (DoA) estimation is a fundamental task in array processing. A popular family of DoA estimation algorithms are subspace methods, which operate by dividing the measurements into distinct signal and noise subspaces. Subspace methods, such as MUSIC and Root-MUSIC, require the sources to be non-coherent, and are considerably degraded when this does not hold. Recent years have witnessed a growing interest in using deep learning for DoA estimation. Here, deep neural networks learn their mapping from data and replace classic algorithms that are based on specific statistical modelling. However, blackbox neural networks do not share the interpretability, reliability, and flexibility of statistical model based algorithms, such as subspace methods. This talk will present a middle ground approach, following the emerging methodology of model-based deep learning. We will review how deep learning tools can be used to empower subspace methods, instead of replacing them.

By adopting such a hybrid model-based/data-driven approach, we show that one can realize DoA estimators which learn how to divide the observations into distinguishable subspaces. The resulting algorithms leverage data to cope with coherent sources, low SNR and limited snapshots, while preserving the interpretability and the suitability of classic subspace-based DoA estimation.

Nir Shlezinger is an assistant professor in the School of Electrical and Computer Engineering in Ben-Gurion University, Israel. He received his B.Sc., M.Sc., and Ph.D. degrees in 2011, 2013, and 2017, respectively, from Ben-Gurion University, Israel, all in electrical and computer engineering. From 2017 to 2019 he was a postdoctoral researcher in the Technion, and from 2019 to 2020 he was a postdoctoral researcher in Weizmann Institute of Science, where he was awarded the FGS prize for outstanding achievements in postdoctoral research. His research interests lie in the intersection of signal processing, machine learning, communications, and information theory.

Financial fraud ML is characterized by a setting which is both adversarial and suffering from delayed feedback. Fraud is often reported and reviewed by humans, which means that time goes by until it is noticed; during this time, fraudsters are generating new types of attacks. To build models relevant for the present, we need to train on data which is not fully labeled. Standard semi-supervised learning usually partitions the dataset to a small subset of labeled data, and a larger subset of unlabeled data. In this setting, however, all data is labeled only to some extent, without a clear partition. In this talk we will review some theoretical aspects of this, as well as graph-based models for addressing this.

Ami is a research scientist in Meta’s Core Data Science team, where he works on financial fraud and risk problems. He holds a Ph.D. in EE from Tel Aviv University. Despite this, on too many occasions, he still gets mixed up between “concave” and “convex”.

The collection of high-quality labeled medical data is often costly and time-consuming, limited by access to expensive measurement devices and domain experts, which eventually lead to small dataset sizes. Self-supervised learning (SSL) has emerged as a promising approach for training deep learning models in such scenarios, where a dataset consists of a small amount of labeled data and a large amount of unlabeled data. In this study, we present an SSL-based approach for continuous measurement of gait speed using a smartwatch. Gait speed is a crucial predictor of disease progression and overall health in individuals with neurodegenerative diseases such as Multiple Sclerosis (MS), Parkinson's Disease (PD), and Alzheimer's Disease (AD). We used millions of hours of accelerometer data collected from smartwatches to create a pre-trained SSL model for multivariate time series, which we then fine-tuned for the task of gait speed estimation based solely on accelerometer data from a wrist-worn smartwatch. Our results demonstrate the effectiveness of SSL in training deep learning models for continuous measurement of gait speed in neurodegenerative disease populations.

Raz holds a B.Sc. in Computer Science and Neuroscience from Tel-Aviv University. Raz has 7 years of experience as a data scientist, working on Computer Vision and Time Series data. 

The watchlist feature in e-commerce allows users to track items over time and is an important aspect of the shopping journey. This talk introduces a new watchlist recommendation task, which aims to predict the next item the user will click on by ranking items in the watchlist. We propose a recommendation model, Trans2D, that is based on the Transformer architecture, and evaluate our model using a large-scale watchlist dataset from eBay. We show our model is superior to other state-of-the-art models.

Yotam is a researcher of machine learning, working at eBay for the past 5 years. Prior to that, Yotam did his master's degree at the Technion under the supervision of Shaul Markovitch, where he worked on applications of deep learning models of NLP tasks. Yotam’s current research interests mostly revolves around eCommerce rec-sys, and user preference modeling on the one hand and applying NLP methods to user generated content on the other.

Speech and audio modeling is a challenging task due various reasons. First, such signals are extremely long, the common sampling rate for speech signals is 16kHz, while for music is 44.1kHz. Second, unlike text, speech and audio representations are continuous in nature, which makes modeling and sampling difficult. In this talk, I will present an alternative view for generative speech and audio modeling in which we use a discrete representation obtained by neural nets trained in an unsupervised fashion. Equipped with this representation we can adapt recent powerful natural language processing models and demonstrate the ability to capture long-term dependencies in the signal as well as high-quality generations. Specifically, I will present our recent advancements in speech and audio language modeling involving different modalities for model conditioning and various application this can be used for.

Dr. Yossi Adi is an Assistant Professor at the Hebrew University of Jerusalem and a (part-time) Research Scientist at FAIR. Yossi completed his Ph.D. in computer science at Bar-Ilan University. Yossi's research interests are in speech and language processing using machine learning and deep learning models. Yossi's research spans core machine learning and deep learning algorithms, their applications to spoken language processing, and the impact of the technology on social systems.

Are you looking for a way to make your fraud detection models more accurate and reliable? In this lecture, we’ll explore how Generative Adversarial Networks (GANs) can help you tackle the various challenges of AI-driven fraud detection, such as imbalance, lack of positive labeled data, and concept drift. We’ll discuss how GANs can be used to generate synthetic data, and how it can be applied to fraud detection models.

Netanel is a senior data scientist at IBM Security since 2019. His main focus is supervised and unsupervised learning in the areas of fraud and bot detection. In addition, Netanel is currently working on his Masters's degree in Information Systems and Software Engineering at Ben Gurion University where he solves novel Reinforcement Learning problems using Deep learning.