Unlocking the next stage in computer vision with deep neural networks
Who is this presentation for?
- Data scientists
- Professionals with a strong understanding of AI who can engage in conversation around this topic and implement these techniques within their organizations
One major end goal of artificial intelligence and deep learning technologies has always been to mimic how the human brain processes and interprets data through the senses. While much work remains to realize that goal, we’re starting to see real and meaningful progress toward this vision. These tools now enable machines to recreate how the human brain interprets images—essentially giving computers eyes and the ability to see. This concept has major implications for businesses that need to extract meaning from overwhelming quantities of unstructured data, like digital images.
Data scientists at Zillow Group are leveraging computer vision based in deep neural networks to test new ways to estimate a home’s value based on specific image criteria. They’re training their solutions to interpret home attributes—from hardwood floors to granite countertops—to help infer the value of a home.
This technology is in its infancy. The organizations that use it most effectively will be those who know which questions to ask and what challenges to solve first. Jasjeet Thind walks you through the core problems within deep neural networks that his team is working to solve and how organizations can begin to experiment with its capabilities.
- An intermediate knowledge of artificial intelligence and deep learning techniques
What you'll learn
- Understand how Zillow Group uses deep neural networks to build the most accurate system for evaluating homes
- See the opportunities and limitations within deep neural networks, as well as various use cases for the technology
- Learn challenges to overcome and what the future holds for this technology
Jasjeet Thind is the vice president of artificial intelligence at Zillow. His group focuses on machine learning prediction models and big data systems that power use cases such as Zestimates, personalization, housing indices, search, content recommendations, and user segmentation. Previously, Jasjeet served as director of engineering at Yahoo, where he architected a machine learning real-time big data platform, leveraging social signals for user interest signals and content prediction. The system powers personalized content on Yahoo, Yahoo Sports, and Yahoo News. Jasjeet holds a BS and master’s degree in computer science from Cornell University.
Leave a Comment or Question
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)
Diversity and Inclusion Sponsor
R & D and Innovation Track Sponsor
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
View a complete list of O'Reilly AI contacts