Practical AI AI in the browser
Oct 21, 2019
Victor Dibia, a research engineer at Cloudera's Fast Forward Labs, dives into the exciting world of machine learning in browsers. He explains why porting models to the browser captivates developers, emphasizing user privacy and interactivity. The discussion includes TensorFlow.js versatility, allowing for innovative projects like real-time hand tracking and offline training. Dibia showcases practical applications, including image analysis by companies like Airbnb, illustrating how AI can enrich web experiences while maintaining security.
AI Snips
Chapters
Transcript
Episode notes
Benefits of Browser-Based AI
- Running ML models in the browser offers privacy benefits, easier distribution, and enhanced interactivity.
- These advantages make the browser an attractive environment for AI, despite its limitations.
Browser-Based AI Advantages
- Browser-based AI excels in privacy preservation by keeping user data local.
- It also simplifies distribution and enables interactive, low-latency applications.
Distribution Challenges
- Victor Dibia recounts friends abandoning machine learning due to TensorFlow installation difficulties.
- This highlights distribution challenges that browser-based AI can resolve.