Session
Technical Poster Session 3
Location
Utah State University, Logan, UT
Abstract
A novel approach to on-board artificial intelligence (AI) is presented here that is based on state-of-the-art academic research of the well known technique of data pipeline. Algorithm pipelining has seen a resurgence in the high performance computing work due its low power use and high throughput capabilities. The approach presented here provides a very sophisticated threading model combination of pipeline and parallelization techniques applied to deep neural networks (DNN), making these type of AI ap-plications much more efficient and reliable. This new approach has been validated with several DNN models developed for Space application (including asteroid landing, cloud detection and coronal mass ejection detection) and two different computer architectures. The results show that the data processing rate and power saving of the applications increase substantially with respect to standard AI solutions, enabling real AI on space.
Enabling Artificial Intelligence On-Board for Image Processing Applications
Utah State University, Logan, UT
A novel approach to on-board artificial intelligence (AI) is presented here that is based on state-of-the-art academic research of the well known technique of data pipeline. Algorithm pipelining has seen a resurgence in the high performance computing work due its low power use and high throughput capabilities. The approach presented here provides a very sophisticated threading model combination of pipeline and parallelization techniques applied to deep neural networks (DNN), making these type of AI ap-plications much more efficient and reliable. This new approach has been validated with several DNN models developed for Space application (including asteroid landing, cloud detection and coronal mass ejection detection) and two different computer architectures. The results show that the data processing rate and power saving of the applications increase substantially with respect to standard AI solutions, enabling real AI on space.
