Private AI is a repository consisting of 16 notebooks that cover complete Secure and Private AI Scholarship course offered by Udacity and Facebook.
The main goal of Private AI project is to show my progress over the course of the challenge, and how to use PyTorch together with other tools necessary to safely and securely train AI models on distributed private data. Each notebook describes different aspect and technique for preserving privacy. Notebooks walk you through three main cutting-edge technologies for privacy-preserving AI, namely:
- Federated Learning
- Differential Privacy
- Encrypted Computation
Interesting observations and important notes are bolded inside each of the Google Collabs.
Completing the entire course together with accompanying notebooks has multiple benefits (based on Andrew Trask testimony):
- A Competitive Career Advantage – We are setting ourselves apart in the field of ML and privacy protection. With new regulation such as GDPR, enterprises are under pressure to have less freedom with how they use - and more importantly how they analyze - personal information. Bottom Line: Data Scientists aren't going to have access to as much data with "old school" tools, but by learning the tools of Private Deep Learning, YOU can be ahead of this curve and have a competitive advantage in your career.
- Entrepreneurial Opportunities - There are a whole host of problems in society that Deep Learning can solve, but many of the most important haven't been explored because it would require access to incredibly sensitive information about people. Thus, learning Private Deep Learning unlocks a whole host of new startup opportunities for you which were not previously available to others without these toolsets.
- Social Good - Deep Learning can be used to solve a wide variety of problems in the real world, but Deep Learning on personal information is Deep Learning about people, for people. Learning how to do Deep Learning on data you don't own represents more than a career or entrepreneurial opportunity, it is the opportunity to help solve some of the most personal and important problems in people's lives - and to do it at scale.
I wouldn’t be here today if not support of Udacity, Facebook and the whole Slack community. Therefore from this place I would like to acknowledge above mentioned rockstars for tremendous help, support and being by our side every step of the way. 🙏 🙏 🙏 THANK YOU 🙏 🙏 🙏