PyData TLV meetup #15 @ Taboola
Details
This will be our #15 PyData event in Israel! As usual, it will include great lectures by industry experts, mingling and sharing :) All lectures will be held in English.
Many thanks to Taboola for sponsoring and hosting this event!
Schedule
• 18:00 - 18:30 - Gathering, snacks, mingling
• 18:30 - 18:40 - Opening words
• 18:40 - 20:45 - Three Lectures :
-Eating the cake and keeping it whole: maintainable complex algorithmic code in production - Uri Yanover
- Size and Temperature Transferability of Direct and Local Deep Neural Networks for Atomic Forces - Nataly Kuritz
- Deep Learning and Medical Imaging - Bella Fadida
------------- Talk Descriptions -------
Title: Eating the cake and keeping it whole: maintainable complex algorithmic code in production - Uri Yanover
Abstract: Python is amazing for expressing algorithms concisely and robustly for academic purposes. However, going to production means that an engineering team has to be able to own an application code base consisting of hundreds of algorithms, that is reliable, has high and controllable performance and is easy to extend and fix. This talk is about an approach to technology and culture that enables these goals while retaining Python’s fundamental elegance.
----
Title: Size and Temperature Transferability of Direct and Local Deep Neural Networks for Atomic Forces - Nataly Kuritz
Abstract:
A direct and local deep learning (DL) model for atomic forces is presented. We analyze the model’s performance as a function of the number of
neighbors included and show that one can ascertain physical
attributes of the system from the analysis of the deep learning model’s behavior. Finally, we test the size scaling performance of the model, and the transferability between different temperatures, and show that our model performs well in both scaling to larger systems and high-to-low temperature predictability.
Based on : https://arxiv.org/pdf/1804.01151.pdf
----
Title: Deep Learning and Medical Imaging - Bella Fadida
Abstract:
Even though Deep Learning has been very popular in Computer Vision community already since 2012, only in the last years it gained popularity also in the medical imaging domain. In this talk I will present the unique challenges in the medical imaging domain, and how they can be addressed. We will take image segmentation as an example and see the evolution of solutions for this problem.