Eldad Haber, PhD | University of British Columbia
TITLEDeep neural networks - new and old science meet
ABSTRACTNeural 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.
BIOEldad Haber is a scientific an NSERC Industrial Research Chair at the University of British Columbia. Eldad is working in the field of computational inverse problems with applications in machine learning, geosciences and medical imaging. Over the last 20 years, Eldad has written various commercial software packages that have been widely adopted by industry. Eldad has written or co-authored over 150 peer reviewed publications on computational problems and is a U.S. Department of Energy Career Award recipient. After completing his Ph.D, he spent several years as a research scientist with Schlumberger and nine years at Emory University in Atlanta at the Department of Mathematics and Computer Science. In 2011, Eldad co-founded Computational Geosciences Inc and in 2017 he co-founded Xtract.ai.