B1336
Title: Bayesian learning of heterogeneous image sources: A journey through non-parametric models to deep learning architecture
Authors: Rajarshi Guhaniyogi - Texas A & M university (United States) [presenting]
Aaron Scheffler - University of California, San Francisco (United States)
Rene Gutierrez - Texas A and M University (United States)
Abstract: Of late, images from multiple sources at different scales have been routinely encountered in various disciplines. The Bayesian paradigm has the natural advantage of modelling different data sources through carefully constructed hierarchical models and prior distributions. However, this paradigm has been quite under-utilized in modelling multi-source images. Novel approaches are presented, encompassing Bayesian non-parametric models and deep learning architecture to address this methodological problem. The approach is demonstrated to through empirical validation, especially with analyses of high-impact neuroimaging datasets.
