There is an increasing demand within consumer-neuroscience (or neuromarketing) for objective neural measures to quantify consumers’ preferences and predict responses to marketing campaigns. However, the properties of EEG raise difficulties for preference prediction: small datasets, high dimensionality, elaborate manual feature extraction, intrinsic noise, and between-subject variations. We aimed to overcome these limitations by combining unique techniques within a Deep Learning (DL) framework, while providing interpretable results for neuroscientific and decision-making insight. In this study, we developed a DL model to predict subject-specific preferences based on their EEG data. In each trial, 213 subjects observed a product’s image, from 72 possible products, and then reported how much they were willing to pay (WTP) for the product. The DL employed EEG recordings from product observation to predict the corresponding reported WTP values. Our results showed 75.09% test accuracy in predicting high vs. low WTP, surpassing other models and a manual feature extraction approach. Meanwhile, network visualizations provided the predictive frequencies of neural activity, their scalp distributions, and critical timepoints, shedding light on the neural mechanisms involved with evaluation. In conclusion, we show that DLNs may be the superior method to perform EEG-based predictions, to the benefit of decision-making researchers and marketing practitioners alike.

Prof. Dino Levy is an associate professor at the Marketing Department at Coller School of Management, Tel-Aviv University and the head of the Neuroeconomics and Neuromarketing lab since 2012. He is also a member of the Sagol School of Neuroscience at Tel-Aviv University and a visiting scholar at the Institute for the Interdisciplinary Study of Decision Making at NYU. In his lab they use an interdisciplinary approach, which involves quantitative economic theories, combined with advanced behavioral methods and theoretical models from psychology, marketing, and economics with neuroscience techniques such as functional magnetic resonance imaging (fMRI) and Electroencephalography (EEG). The main aim of his studies is to try and better understand how we make decisions and what are the neural mechanisms underlying value-based choices. The projects in the lab range from examining the neural correlates of value computations and the common currency network, deciphering the neural mechanisms of irrational choice behaviors both in humans and in basic organisms, through looking for a common denominator between basic visual perception and value computations, to projects that aim to predict future preferences and population success of marketing stimuli using neural signals.

13:00 - 13:10

 Moderator: Yorai Fainmesser, Co-Founder, General Partner at DisruptiveAI VC, Artificial Intelligence, Big Data - Strategic Expert

13:10 - 13:30 - Deep Learning for Electronic Signals

 Ziv Freund, Head of AI R&D Group, EW & SIGINT – Elisra – Elbit Systems

Yoni Birman is the Cloud and AI Security Research Director of Huawei's Tel Aviv Research Center (Toga Networks).

The group solves cyber and privacy challenges for Huawei Cloud and AI Security Business Unit such as: Endpoint/Application/ Data/ML protection in the cloud domain using AI.

Prior to his current position Yoni served for 10 years in Unit 8200 in various positions in the domains of D.S and cyber security. His last position was the Head of Cyber Security R&D department.

Yoni is an External Assistant professor of Computer Science at Reichman University.

Yoni obtained his PhD at Ben-Gurion University, Software and Information Systems Engineering Department.

IP hijack attacks are strong attacks on the Internet routing system that allows an attacker to deflect traffic through its network and form man-in-the-middle attack.  As such these attacks are often undetected, which allows the attacker, e.g., to perform long term espionage.
To detect such attacks we suggest several tools that are based on deep learning, and enable to build robust detection tools including: supervised DL based on network level (such as BGP announcements) supervised and  non-supervised methods and a method, which is based , for the first time, on route geography.
 

Professor of Electrical Engineering at Tel Aviv University. Before joining Tel Aviv University, he worked for four years at the Networking Center of Bell Labs, Holmdel, NJ. He published seminal papers in the fields of caching, routing, IP hijack attacks, and network measurements. In recent years, he has been working on usage of AI to solve networking problems in the areas of traffic classification and detection of routing manipulations.

5G Network Data Analytics Function (NWDAF)  provides the ability to collect variety of data from all over the mobile 5G Network .
On top of this data specific network data analytics are generated for insights and actions .
In this talk we are going to go through NWDAF NF Load prediction use case to show how we tradeoff between latency and accuracy.
Will show practical tips and tricks to improve latency and our ML tradeoff selector.
 

Boris Rabinovich is a Senior Data Scientist at Amdocs. Author of several patents and academic papers. Prior to Amdocs, Boris worked in multiple Machine Learning roles and his experiences span a wide variety of ML projects including end-to-end implementation of Time series forecasting, Recommendation systems, Predictive Modeling and NLP problems.

14:30-14:40

 Uri Eliabayev, Founder of Machine and Deep Learning Israel Community

14:40 - 15:00 - Using AI to Increase Hardware Performance

 Avishai Wagner, Applied Research Scientist, Intel IT AI Group

In this talk I will share our journey at Shops on creating product embeddings, I will discuss tradeoffs of using internal Meta systems and services vs. customized ones. I will discuss how different products (Instagram/Facebook) affect our model selection and optimization methods, and how all of these can be taken into consideration to provide our customers with the best experience.

Ayelet is an ML engineer at Meta and was one of the founding team members of multiple Meta Shops initiatives. She was responsible for building several of the major building blocks behind the Shops recommendation system. Besides working at Meta, Ayelet has recently taken up surfing and is an amateur hiking guide. Ayelet holds a B.Sc. in EE from BGU.

The quest for algorithms that enable cognitive abilities is an integral part of machine learning and appears in many facets, such as virtual assistants and visual reasoning. A cognitive system must be capable of processing details from the multiple sensors that pound a device's computation engine. Interpreting observed objects requires an understanding of their semantics. Additionally, it must be sensitive to and pick out relevant nuances relevant to the task. During this presentation, we will present ways to assess and improve perception. We will explore ways to leverage large-scale models (such as CLIP). As a final step, we propose a novel attention mechanism, called Factor Graph Attention, which can operate on any data utility and distinguish useful signals from distracting ones. Our discussion will focus on the limitations of current methods: (i) models may solve the dataset, but not the task directly; (ii) supervised methods are limited by the curated datasets. Further, we demonstrate novel arithmetic capabilities to reason over visual data, as well as state-of-the-art performance on various tasks, such as visual dialog.

Idan Schwartz is the head of research of Spot by Netapp, and also a postdoctoral in the Computer Science department at the Deep Learning Lab led by Prof. Lior Wolf. Idan's research focuses on cognition in deep learning, particularly in the multimodal domain, such as visual question answering and visual dialog. These cognitive processes include perception, comprehension, attention, and decision-making.