Training deep learning networks is often seen as a dark art. Hanlin Tang demystifies the process, sharing lessons learned from building AI algorithms across multiple verticals and tips and tricks for designing models. Hanlin also offers an overview of the Intel Nervana deep learning stack, which accelerates the iteration cycle for data scientists.
Hanlin Tang is an algorithms engineer in Intel’s AI products group, where he builds deep learning models in computer vision and applies these models to various domains, ranging from satellite imagery to computational neuroscience. He also leads the group’s AI projects with defense and intelligence agencies. Hanlin joined Intel through its acquisition of deep learning startup Nervana Systems. Hanlin holds a PhD in biophysics from Harvard, where his work investigated recurrent neural networks in human brain. His research has appeared in scientific journals such as Neuron, Scientific Reports, and eLife.
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org