Deep Recommender Systems at Facebook feat. Carole Jean Wu, Stanford MLSys Seminar Episode 24

Episode 24 of the Stanford MLSys Seminar Series Designing AI systems for deep learning recommendation and beyond Speaker: CaroleJean Wu Abstract: The past decade has witnessed a 300, 000 times increase in the amount of compute for AI. The latest natural language processing model is fueled with over trillion parameters while the memory need of neural recommendation and ranking models has grown from hundreds of gigabyte to the terabyte scale. This talk introduces the underinvested deep learning personalization and recommendation systems in the overall research community. The training of stateoftheart industryscale personalization and recommendation models consumes the highest number of compute cycles among all deep learning use cases at Facebook. For AI inference, recommendation use cases consume even higher compute cycles of 80. What are the key system challenges faced by industryscale neural personalization and recommendation models This talk will highlight recent advances on AI system development f