RESEARCH

All topics

Causal Inference

Neuroscience

NLP

Vision

Urban Planning and Smart Cities

Neuroscience and Psychology

AI and Education

Health-Biomedicine

Fundamentals of AI and DS

Environment

Economy and Finance

Digital Humanities

AI, Ethics & Law

AI in the Physical Sciences

AI for social good

AI-based methodologies for phylogeny: model selection and tuning dataset-specific search Parameters

Research

Aug 3rd, 2023

AI-based methodologies for phylogeny: model selection and tuning dataset-

Researchers: Prof. Tal Pupko (Shmunis School of Biomedicine and Cancer Research), Prof. Yishay Mansour (Computer Science), and Prof. Itay Mayrose (Plant Sciences)

Health-Biomedicine
Fundamentals of AI and DS

Research

Aug 3rd, 2023

Geometry-Oriented Dependence Measures

Researcher: Dr. Anatoly Khina (Electrical Engineering)

Fundamentals of AI and DS

Generalized regression discontinuity design with multiple time periods and comparison groups for causal inference: theory and practice

Research

Aug 3rd, 2023

Generalized regression discontinuity design with multiple time periods and

Researchers: Dr. Daniel Nevo (Mathematical Sciences), Dr. Itay Saporta-Eksten (Economics), and Dr. Analia Schlosser (Economics)

Causal Inference
Fundamentals of AI and DS

Research

Dec 20th, 2022

Machine and Deep Learning for Smart Electromagnetism and Photonics

Researchers: Haim Suchowski (Physics) & Nadav Cohen (Computer Science)

Fundamentals of AI and DS
AI in the Physical Sciences

Artificial Intelligence has emerged as a powerful approach that has already led to many breakthroughs in multiple scientific and technological fields in the past decade.

Deep Learning, inspired by the layered and hierarchical deep architecture of the human brain, has emerged as an efficient means to design photonic structures.

Our current proposal stems from the complementary expertise of the two groups and from the realization that Deep learning strength can be further leveraged to address inverse design challenges in physics and, in particular, in electromagnetism’s sub-wavelength inverse design spanning the large spectrum of electromagnetic and photonics applications.

More specifically, using recently introduced DL methods and our recent achievements, we plan to address challenging inverse design tasks in electromagnetism such as sensing with nano-photonics, novel 5G and Wifi antennas as well as integrated photonics for quantum information and LIDARs.

General Falsification Tests for Instrumental Variables

Research

Feb 24th, 2022

General Falsification Tests for Instrumental Variables

Researchers: Dr. Oren Danieli (Economics), Dr. Daniel Nevo (Statistics & Operations Research), Dr. Dan Zeltzer (Economics)

Fundamentals of AI and DS
Economy and Finance
AI for social good

Instrumental variable (IV) estimation is a widely used method that supports high stakes government policies and business decisions, when controlled experiments are not feasible or when a treatment is not successfully delivered to every unit in a randomized experiment.

In this research project, we will develop statistical methods for assessing the validity of such designs. IV designs rely on exclusion restriction assumptions that are not directly testable and that are therefore challenging to assess empirically. In this context, this project aims to formalize the logic of falsification tests, a set of tests that leverage contextual knowledge about the absence of causal links (for example, from future to past outcomes) to test the validity of candidate instruments.

We will establish that IV falsification tests can be mapped to a class of prediction problems that can leverage current machine learning methods. Based on this conceptualization, we will develop general methods that would both improve falsification test efficiency and help guide the construction of such tests.

These methods will be particularly applicable to research using large datasets with many candidate variables that can be used for falsification, an increasingly common situation for which no formal methods currently exist. Developing methods for evaluating and improving the validity of these common research designs entails clear societal benefits.

Balancing Fair use and copyright in The Presence of Big and Synthetic Data. Photo by fabio on Unsplash

Research

Feb 24th, 2022

Balancing Fair use and copyright in The Presence of Big and Synthetic Data

Researchers: Dr. Roi Livni (Electrical Engineering)

Fundamentals of AI and DS
AI, Ethics & Law
AI for social good

One of the exciting recent developments in Machine Learning and AI is the success of Deep Learning algorithms to utilize big data towards solving some of the most emerging and important problems we face today.

This success, though, comes with a price. Often, machine learned models exploit information generated and owned by individuals that contains sensitive, private, copyrighted material.

It is then an emergent question how to harness these learning machines in a fair setting that enables the exploitation of the data, while not breaching the individual's rights.

In this proposal we focus on the question of generating synthetic data. We consider a setting where a learner has access to publicly available data, and may exploit it for fair-use to generate similar data, but the learner is not allowed to copy or to breach intellectual property (IP) rights.

The first challenge we face is to correctly model the question of IP-rights and fair use. In particular, the project will aim to propose different notions and criteria for fair-use as well as study their statistical and computational complexity.

The Center for Theory of Deep Learning. Fundamentals of AI

Research

Sep 23rd, 2021

The Center for Theory of Deep Learning

Researchers: Prof. Amir Globerson (Computer Science), Dr. Tomer Koren (Computer Science), Prof. Yishay Mansour (Computer Science), Dr. Nadav Cohen (Computer Science), Prof. Lior Wolf (Computer Science), Prof. Raja Giryes (Electrical Engineering), Prof. Meir Feder (Electrical Engineering), Dr. Roi Livni (Electrical Engineering), Prof. Saharon Rosset (Mathematical Sciences)

Fundamentals of AI and DS

Much of the recent success of AI relies on deep learning techniques. However, these remain poorly understood from a theoretical perspective.

In this project, led by Prof. Amir Globerson, we take advantage of an exceptionally strong and diverse group of TAU researchers with expertise in the field to tackle challenging questions and their practical implications.

A key aspect of this project involves forming new cross disciplinary collaborations that will be able to uncover original aspects of the core questions in this area. To this end, we held a successful two-day retreat for the faculty members in the group and their graduate students at the Elma Hotel in Zikhron Yaakov in February 2023.

Deep Learning Theory Retreat >>

Research

Aug 11th, 2021

The phylogenetic tree reconstruction game: developing reinforcement-learning

Researchers: Tal Pupko (Life Sciences), Yishay Mansour (Computer Science), Itay Mayrose (Life Sciences)

Health-Biomedicine
Fundamentals of AI and DS

The following two fields have never interacted before: reinforcement learning and molecular evolution. Here we develop a reinforcement-learning algorithm to solve the challenge of reconstructing phylogenetic trees, which are used to describe the evolutionary relationships among a set of genome sequences. The current tools for phylogenetic tree reconstruction integrate heuristic approaches to evaluate only a subset of all potential trees, thus all suffer from the known trade-off between accuracy and running time. Although recent studies have shown the potential of harnessing AI-based methods to reconstruct phylogenetic trees, the question regarding the overall tree-search strategy remains open. In our study, we provide a novel methodology for predicting the maximum-likelihood tree. We demonstrated that a framework that optimizes a sequence of two "lookahead" moves into the horizon, is superior compared to a framework which optimizes a single move at a time (see the attached figure). These preliminary results thus suggest that our proposed paradigm, that uses reinforcement-learning techniques to learn an optimal strategy for the tree search, can boost tree search-heuristics without compromising accuracy.

The full article >

Research

Aug 4th, 2021

Towards Autonomous Exploratory Data Analysis

Researchers: Prof. Tova Milo (Computer Science), Prof. Daniel Deutch (Computer Science)

Fundamentals of AI and DS

In the era of Big Data, exploratory data analysis (EDA) is gaining great importance. Yet, EDA is still a difficult process, especially for non-expert users, as it requires deep understanding of the investigated domain and the particular context. Consequently, users may skip significant analysis actions and overlook important aspects of the data. In this research, we aim to set the ground for employing Deep Reinforcement Learning (DRL) techniques in the context of EDA. We suggest an end-to-end framework architecture coupled with an implementation of each component. Our goal is the development of DRL models and techniques for facilitating a full-fledged, autonomous solution for EDA.

Research

Jul 12th, 2021

Multiple testing for particle picking in cryo-EM

Researchers: Tamir Bendory (Electrical Engineering), Amichai Painsky (Industrial Engineering)

Fundamentals of AI and DS

The goal of this research is to design a computational framework for particle picking in single-particle cryo-electron microscopy (cryo-EM) based on fundamental statistical principles. This should be contrasted with many existing techniques in the cryo-EM field, which are based on different heuristics and are not supported by solid statistical or mathematical justifications.

To accomplish our aim, we develop two computational frameworks. The first approach is based on spatial multiple testing based on topological features. The second project studies the detection of particle's locations as a change point detection problem, which is a well-studied problem is time series analysis.

RESEARCH

What are you interested in?