Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “caffe”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

3 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2001

Novel method to assess gastric emptying in humans: the Pellet Gastric Emptying Test

To further validate the Pellet Gastric Emptying Test (PGET) as a marker of gastric emptying, a randomized, four-way crossover study was conducted with 12 healthy subjects. The study consisted of oral co-administration of enteric coated caffeine (CAFF) and acetaminophen (APAP) pellets in four treatment phases: Same Size (100 kcal), Fasted, Small Liquid Meal (100 kcal), and Standard Meal (847 kcal). The time of first appearance of measurable drug marker in plasma, t(initial), was taken as the emptying time for the markers. Co-administration of same size enteric coated pellets of CAFF and APAP (0.7 mm in diameter) revealed no statistically significant differences in t(initial) values indicating that emptying was dependent only on size and not on chemical make-up of the pellets. Co-administration of different size pellets indicated that the smaller 0.7-mm diameter (CAFF) pellets were emptied and absorbed significantly earlier than the larger 3.6-mm diameter (APAP) pellets with both the Small Liquid Meal (by 35 min) and the Standard Meal (by 33 min) (P<0.05). The differences in emptying of the pellets were not significant in the Fasted Phase. The results suggest that the pellet gastric emptying test could prove useful in monitoring changes in transit times in the fasted and fed states and their impact on drug absorption.

NASA Discipline Regulatory Physiology↗
DOE OSTI2019

REMODEL: Rethinking Deep CNN Models to Detect and Count on a NeuroSynaptic System

In this work, we perform analysis of detection and counting of cars using a low-power IBM TrueNorth Neurosynaptic System. For our evaluation we looked at a publicly-available dataset that has overhead imagery of cars with context present in the image. The trained neural network for image analysis was deployed on the NS16e system using IBM's EEDN training framework. Through multiple experiments we identify the architectural bottlenecks present in TrueNorth system that does not let us deploy large neural network structures. Following these experiments we propose changes to CNN model to circumvent these architectural bottlenecks. The results of these evaluations have been compared with caffe-based implementations of standard neural networks that were deployed on a Titan-X GPU. Results showed that TrueNorth can detect cars from the dataset with 97.60% accuracy and can be used to accurately count the number of cars in the image with 69.04% accuracy. The car detection accuracy and car count (–/+ 2 error margin) accuracy are comparable to high-precision neural networks like AlexNet, GoogLeNet, and ResCeption, but show a manifold improvement in power consumption.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Scalable Deep Learning via I/O Analysis and Optimization

Scalable deep neural network training has been gaining prominence because of the increasing importance of deep learning in a multitude of scientific and commercial domains. Consequently, a number of researchers have investigated techniques to optimize deep learning systems. Much of the prior work has focused on runtime and algorithmic enhancements to optimize the computation and communication. Despite these enhancements, however, deep learning systems still suffer from scalability limitations, particularly with respect to data I/O. This situation is especially true for training models where the computation can be effectively parallelized, leaving I/O as the major bottleneck. In fact, our analysis shows that I/O can take up to 90% of the total training time. Thus, in this article, we first analyze LMDB, the most widely used I/O subsystem of deep learning frameworks, to understand the causes of this I/O inefficiency. Based on our analysis, we propose LMDBIO—an optimized I/O plugin for scalable deep learning. LMDBIO includes six novel optimizations that together address the various shortcomings in existing I/O for deep learning. Lastly, our experimental results show that LMDBIO significantly outperforms LMDB in all cases and improves overall application performance by up to 65-fold on a 9,216-core system.

97 MATHEMATICS AND COMPUTING↗