HVAC optimization using Reinforcement Learning & Embryo selection using AI

Agenda:

18:00-18:30 Embryo selection using AI (Stanko Kuveljic)
18:30-19:00 HVAC optimization using Reinforcement Learning (Nina Marjanovic)
19:00-19:30 Beer & networking

HVAC optimization using Reinforcement Learning

Summary:
Most buildings lose more than 10% of energy due to poorly optimized heating, cooling and ventilation devices. Using Reinforcement Learning, we tried to optimize energy consumption with a significant reduction in the cost of heating and cooling

Bio:
Nina Marjanovic works as a data scientist in SmartCat. She is interested in biologically inspired algorithms and text processing.

Embryo selection using AI

Summary:
In vitro fertilization often results in multiple pregnancy, because doctors implant few embryos in mother to make higher chance of succeeding. Mothers carrying twins or triplets have an increased incidence of preeclampsia, maternal haemorrhage, operative delivery, uterine rupture, and preterm labor. Idea is to find single embryo that has the highest probability to implant and results in a live born baby. Data is presented as time lapse video of developing embryo (first 5 days). In this talk we would deep dive into several neural network architectures that are used in the project. Starting with U-net for embryo segmentation and extraction from raw videos, then unsupervised convolutional neural networks and recurrent neural networks for video processing. Also, we explore possibility of using external data source (patient and embryo records) alongside neural network in order to train end to end deep learning solution.

Bio:
Stanko Kuveljic is a data scientist at SmartCat. He graduated master degrees at Faculty of Technical Sciences in Novi Sad with master thesis “The Review of Neural Networks with examples of applications”. He enjoys to work with Spark and Tensorflow. Stanko in few words: Cats, Food, Games, Music, Manga, Anime and FOR THE HORDE!