Badging and RSVP policy:Please help us with badging and sign-up for this Meetup with your first and last name by answering the question during RSVP. That way we can print out the badges ahead of time and speed up the sign-in process. Thanks! We would also like to reiterate our RSVP policy: If you are on the waitlist and we think the event venue will be at or close to capacity you will have to wait until 6:45 before we allow you into the room. If you are RVSPed we will keep your spot available until 15 minutes before the announcements, after that your spot will be given to someone present on the waitlist. If the room is filled at anytime earlier, we will deny entrance. Schedule: 6:00-6:50pm Networking and light food 6:50-7:00pm Announcements 7:00-7:50pm TensorFlow - Magnus Hyttsten 7:50-8:30pm Temporal Anomaly Detection in Streaming Data with LSTM networks - Marion Le Borgne Abstract/Speaker Bios: Abstract: Did you know that you can use TensorFlow to caption images, understand text, and generate art? Join this talk for a tour of the latest projects using TensorFlow for computer vision, natural language processing, and computer generated artwork + learn some TensorFlow stuff. I'll share my favorite models for each domain, show live demos you can try at home, and share educational resources you can use to learn more. This requires no special background in machine learning. Bio: Magnus Hyttsten works a Developer Advocate for TensorFlow at Google. He is an uncompromising software technologist and product marketing fanatic that likes to work in fast paced environments. He enjoys studying everything about ML, and statically typed programming languages. Right now, he is extremely passionate about TensorFlow! Abstract: We are living in an area with an ever growing number of sensors, where accurate anomaly detection is critical. But what does it take to automate stream processing? How do we create machine learning models that can keep up with exploding numbers of data streams? This talk covers how to leverage LSTM (Long Short-Term Memory) to create applications that can detect anomalies in real time, automatically and without the need for data labeling. Bio: Marion Le Borgne is a Machine Learning Researcher and the Co-Founder of NeuroTechX, the international neurotechnology network. She started her career as a Venture Capital Analyst at Partech International Ventures which led her to dive deeper in the world of Data Science and Machine Learning. She's a big advocate for HTM, a neural network strictly based on neuroscience and the physiology of the cortex, that she contributed to when she was a Senior Software Engineer at Numenta.
