Published Mar 10, 2017

Scaling Deep Learning: Systems Challenges & More with Shubho Sengupta - #14

Shubho Sengupta, Research Scientist at Baidu, delves into the pressing challenges of scaling deep learning, emphasizing the need for diverse datasets beyond ImageNet and the pivotal role of hardware innovation in overcoming current processor and GPU limitations. Sengupta also dissects the complexities of model scalability, network architecture, and the necessity of manual optimizations to advance AI systems.
Episode Highlights
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) logo

Popular Clips

Episode Highlights

Related Episodes