Daniel Soudry is an assistant professor and a Taub Fellow at the Department of Electrical Engineering at the Technion. His first work focsed on Neuroscience, attempting to understand how neurons work in the brain. He then continued to a post-doc at Columbia University, where he discovered his interest in both the practical concerns and theory of deep neural networks. This episode focuses on Daniel's research work on questions such as how to make neural network work with low numerical precision, and when are SVM and Logistic Regression the same thing? 
We also talk with him about his path in academia and the journey to discover his research interests.

Theory and Practice of Deep Neural Networks, with Daniel Soudry

Unsupervised is a podcast about Data Science in Israel. At each episode we interview an industry professional or a researcher from academia and discuss different aspects and problems in data science. We want to give a peek to what’s going on with data science across the Israeli industry and also to talk about different algorithms, tools, papers, methods and pretty much everything that’s interesting and related to Data Science and Machine Learning.

The podcast is aimed to data science professionals and researchers, as well as for those who work and collaborate with data science teams and beginners in the field.

All Episodes are recorded in Hebrew.
We want to thank Samsung Next for hosting us.

Technology

Tech News

Podcasting

Gadgets

Software How-To

What is the difference between a data competition and the day to day work as a data scientist? what lessons and tricks can we learn from Kaggle and what pitfalls should we look out for? Nir Malbin, a Kaggle Master and one of the first kaggle competitors in Israel would share with us his thoughts and insights from his long time experience at Kaggle.

Where Kaggle meets the real world

How to learn from noisy data? Can you use free text to generate labels in an unsupervised manner? Jonathan Laserson, Lead AI researcher is Zebra Medical, tells us how they built the world's largest data set of chest X-ray images (1M) and trained a network that detects over 40 findings. Jonathan did his PhD in computer science at Stanford, where he specialized in Bayesian methods and probabilistic graphical models.

Creating your labeled training set, with Jonathan Laserson

The field of privacy in machine learning is becoming increasingly important. With legislation like GDPR, it is becoming necessary for us, data scientists, to be mindful about privacy concerns related to the applications we develop. In this episode we interview Ran Gilad Bachrach, a researcher at Microsoft Research, that tells us about privacy in machine learning. We'll talk about differential privacy, about homomorphic encryption and how it enables training models on encrypted data, and about secure multi party computation - a field who's goal is to help different parties train models together, even when they can't share their data with one-another.

Privacy in Machine Learning

AI and ML algorithms are becoming increasingly popular, being implemented in finance, health and law enforcement systems. Mistakes these algorithms can make can have tremendous impact on people’s lives, leading to many ethical and legal questions; how do we define fairness in this context? On what personal rights do these algorithms affect? How can people appeal decisions made by algorithms? These questions, in turn, pose computational challenges, like improving the explainability of algorithms and enforcing algorithmic fairness toward minority groups. In this episode we talk to Gal Yona, from Weitzmann institute, and Yafit Lev-Aretz, from City University of New York. Together they provide us with an introduction to the hot topic of fairness in AI, from computational and legal perspective.

Theory and Practice of Deep Neural Networks, with Daniel Soudry

Download our free app to listen on your phone