Deep Learning and Vision

While Convolutional Neuronal Network (CNN) is not a new topic, it is not until 2013 that this topic got huge attention from academia and industry. Indeed, the overwhelming majority of the talks at the 2015 CVPR conference where about deep learning. Also, companies that are involved in big data such as Google, Facebook, and many others, have invested heavily in topics related to CNNs.

CNNs have outperformed most vision algorithms in classification tasks. Deep learning is revolutionizing vision and artificial intelligence.

Innovative companies will present recent advances and applications in deep learning for vision at our October meetup.

Rough agenda:

6 - 6:30: Networking and Pizza

6:30 - 7:20: Speakers

(1) Professor Tomaso Poggio from MIT (http://cbmm.mit.edu), "Visual Cortex and Deep Networks".

(2) Daniel McDuff from Affectiva (http://www.affectiva.com/), "Deep Emotion Learning: Mining the World’s Largest Facial Expression Dataset".

(3) Barton Fiske from Nvidia (http://www.nvidia.com/page/home.html), "Accelerated Deep Learning with GPU’s".

7:20 - 7:30: 1 min pitches from audience. Need help? Looking for a job? Let us know.

7:30 on: More networking.

Location/Parking: the Microsoft NERD center is a short walk from the Kendall Sq. T stop, located adjacent to the Charles River. There's usually street-parking to be found on side streets (such as Ames St.). There's also a garage in the NERD center, $10 flat fee after 4pm. Just remember to bring your ID to get into the NERD center.