top of page
OUR SPEAKERS
Share on:
Kuritz Natalia, AI Decision Scientist at Anaplan. She compleeted her Ph.D. in the Electrical Engineering faculty at Tel Aviv University. Holds M.Sc. in Computational Material Sciences from Weizmann Institute and B.Sc in Chemistry and Biology from Tel-Aviv University. She authored and co-authored nine articles in scientific journals and presented them in international conferences. Her research focuses mainly on the development, implementation, and customization of novel computational methods to provide predictions and explanations for a wide range of complex systems and measurements including physical and biological complex systems, health care data and financial data.
She has fifteen years of academic and industry technological R&D experience.
Nataly Kuritz
AI Decision Scientist | Researcher
English, Hebrew, Russian
Languages:
Location:
Raanana, Israel
Can also give an online talk/webinar
Paid only. Contact speaker for pricing!
MY TALKS
Size and Temperature Transferability of Direct and Local Deep Neural Networks for Atomic Force
Data / AI / ML, General, Innovation, Women in Tech
The research in the field of materials discovery and characterization for
various modern industry applications are long, cumbersome, and expensive. An approach that was developed in the last decade is to use machine learning algorithms to build on the fly computationally cheap predictors for the energy, forces, and other physical properties. This approach enables the performance of calculations with an accuracy that is close enough to fully quantum calculation but with running speeds that are more than 100 times faster. This lecture covers problem presentation and formulation, data preparation and feature extraction, as well as Deep Neural Network architecture, explainability, interpretability, and scientific insights it provides.
Based on: https://journals.aps.org/prb/abstract/10.1103/PhysRevB.98.094109
The video here is not exactly the same lecture but based on same reaserch
Machine Learning And Deep Learning - Intuitive start
Data / AI / ML, Professional Development, Product, Innovation, Inspirational, Women in Tech
This is a basic and more didactic lecture/workshop for beginners that can fit for those who just start their way in the world of AI.
Usually, I'll fit the content for the audience - either software engineers, entrepreneurs, product managers, domain experts, or anyone who wants to understand the basics (students and children are also included).
Where to start? Which questions should you ask?
I'll focus on gaining intuition and interpretation of the technical stuff.
If time allows, we can and also deep dive into basic procedures and statistics and math.
Caution! Blind spots of your model
Data / AI / ML, Entrepreneurship, Product, Innovation
Let's talk a bit about the interpretability of the AI model.
What should you check about the suggested (AI) model?
Which steps in your pipeline can cause blind spots, how to indicate, define, and fix them?
Size and Temperature Transferability of Direct and Local Deep Neural Networks for Atomic Force
Completed
true
Visible
true
Order
3
Machine Learning And Deep Learning - Intuitive start
Completed
true
Visible
true
Order
2
Caution! Blind spots of your model
Completed
true
Visible
true
Order
3
Completed
false
Visible
false
Order
100
Completed
false
Visible
false
Order
100
Completed
false
Visible
false
Order
100
Completed
false
Visible
false
Order
100
bottom of page