PER DATA AD ASTRA: How to connect artificial intelligence and (shooting) stars?

Topic

You like science and scientific breakthroughs, but your job and profession is data science and you think that these two aspects cannot easily be connected? Maybe you are not even aware of how easily you yourself can become a part of important and interesting scientific research, how important and useful your knowledge and skills can be for the scientific advancements and science development, while at the same time enjoyable and valuable experience.

During this meetup, Dušan Pavlović will give an example of such connection: 

He will talk about how computer vision, deep learning, and research on meteors (shooting stars) overlap. You will find out how relatively easy you can apply your knowledge of neural networks to solve the problem of automatic detection of meteors in astronomic data made by radio detectors. This problem is one of the most complex ones in this field and our understanding of different problems in the Solar System depends on it. 

Also, you will have a chance to learn more about different sources of big data which usually wait to be noticed by data scientists. Alos, you will learn the basics of solving problems of image segmentation and using U-net architecture in PyTorch. Finally, you will see that with these tools and similar projects, you can relatively easily return to industry.

Apply Data Science on scientific data!

* The lecture will be held in Serbian.

 

See you on March 23rd, at 6 PM and don't forget to register!