Deep learning is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using multiple processing layers, with complex structures or otherwise, composed of multiple non-linear transformations.
Power platform is a premier architecture for Deep Learning workloads as showed by University of Maryland Baltimore County, the University of Illinois, and the STFC-Hartree Centre. These article show that POWER8 is ideal for deep learning, big data, and machine learning due to its high performance, large caches, 2x-3x higher memory bandwidth, very high I/O bandwidth, and of course, tight integration with GPU accelerators.
The OpenPOWER Deep Learning Software Distribution is available for Ubuntu/ppc64el, and can be downloaded easily.
You can learn more about Deep Learn more about this framework reading Dr. Michael Gschwind article entitled New OpenPOWER Software Distribution Puts Deep Learning a Click Away