» » »

Deep neural networks - new and old science meet

Eldad Haber

Neural networks have revolutionize many tasks in computer vision and interpretation, and will have significant rolein earth science tasks such as inversion, geological interpretation, prediction of earth parameters and water discovery.The talk will be divided into two parts. In the first part we will show that deep neural networks can be interpreted asdiscretizations of Partial Differential Equations that have been used for modeling for a very long time. This understandingcan help us design an appropriate network architecture that is task dependent and improve the network performance.In the second part of the talk, we discuss how such architectures can solve some problems in earth science, in particular, mapping of water and minerals, geological mapping, magnetic data segmentation and finding horizons in seismic data.

Speaker: Eldad Haber, Univ. of British Columbia

Monday, 01/13/20


Website: Click to Visit



Save this Event:

Google Calendar
Yahoo! Calendar
Windows Live Calendar

Green Earth Sciences Building

367 Panama St, Room 104
Stanford University
Stanford, CA 94305

Website: Click to Visit