Abstract: With the support of big-data and big-compute, deep learning has reshaped the landscape of research and applications in artificial intelligence. Whilst traditional hand-guided feature engineering in many cases is simplified, the deep network architectures become increasingly more complex. A central question is if we can distill the minimal set of structural priors that can provide us the maximal flexibility and lead us to richer sets of structural primitives that potentially lay the foundations towards the ultimate goal of building general intelligent systems.

In this talk I will introduce my Ph.D. work along the aforementioned direction. I will show how we can tackle different real world problems, with carefully designed architectures, guided by simple yet effective structural priors. In particular, I will focus on two structural priors that have proven to be useful in many different scenarios: the multi-scale prior and the sparse-connectivity prior. I will also show examples of learning structural priors from data, instead of hard-wiring them.

Bio: Saining Xie is a Ph.D. candidate in Computer Science at UC San Diego, working with Zhuowen Tu. His research interests span a wide range of topics across computer vision and machine learning. During his PhD he has also spent time at NEC Labs, Adobe Research, Facebook Al Research, Google Research and DeepMind. He is a recipient of Marr Prize Honorable Mention award in 2015 and the Google Ph.D. fellowship in 2017.

Homepage: http://vcl.ucsd.edu/~sxie/?_ga=2.61392812.1209023144.1526304578-1826654341.1526304578