ML in the real world-NLP of legal documents and PyTorch - 6 common mistakes

This is a past event

227 people went

Amobee

מנחם בגין 125 מגדל היובל, בניין קרית הממשלה · Tel-Aviv

How to find us

לבניין יש שתי כניסות: קריית הממשלה ומגדל היובל. עלו במעליות מגדל היובל לקומה 25, חצו את הקומה ועלו במעלית נוספת לקומה 36

Location image of event venue

Details

In this meetup we have two talks about real-world usage of machine learning. Expect a technical talk which requires understanding of NLP concepts and some familiarity with the PyTorch library.

Agenda:
18:00-18:20 Gathering and Networking
18:20-18:50 Legal NLP / Uri Goren, CTO @ Bestpractix
18:50-19:05 Snacks, Beer and Networking
19:05-19:35 PyTorch 6 Common Mistakes / Shahar Gigi, Data Scientist @ MissingLink.ai
19:35-20:00 Networking and Discussions

Legal NLP:
Legal document analysis is a special case of NLP. On the one hand - legal documents tend to be very long, and require expertise, but on the other hand, they are for more structured than free text.
In this talk we would cover 3 techniques that take advantage of these properties for efficient labeling, synonyms and named-entity recognition.

PyTorch - 6 common mistakes:
Instead of spending years in building a strong intuition and a set cheats and tricks, learn the basics from the greats and focus on greater challenges. While deep learning and computer vision bring with them many triumphs over myriad challenges, there are many pitfalls and hacks to work around and debug. On June 30th, 2018, Andrej Karpathy, Director of AI at Tesla, tweeted a short list of first things to check when your neural network isn’t working. In this session, we will learn how to apply these lessons to our own neural networks. Using a computer vision dataset and a PyTorch code sample - we’ll walk through each of these pieces of advice, test it and explain it.

Please RSVP - Space is limited!

The talks are in Hebrew.

A big thanks to Amobee for the hospitality, space and food!