DOE Science Showcase - Deep Learning Neural Networks

One of the Daya Bay detectors
Lawrence Berkeley National Laboratory’s (LBNL) National Energy
Research Scientific Computing Center (NERSC) has implemented
a deep learning data pipeline for the Daya Bay experiment.
Image Credit:  Lawrence Berkeley National Laboratory 

Deep learning neural networks are based on a class of machine algorithms that can learn to find patterns and closely represent those patterns at many levels.  As additional information is received, the network refines those patterns, gains experience, and improves its probabilities, essentially learning from past mistakes.  This is called “deep learning” because the networks that are involved have a depth of more than just a few layers.


Basic deep learning concepts were developed many years ago; with today’s availability of high performance computing environments and massive datasets, there has been a resurgence of deep learning neural network research throughout the science community.  Scalable tools are being developed to train these networks, and brain-inspired computing algorithms are achieving state-of-the-art results on tasks such as visual object classification, speech and image recognition, bioinfomatics, particle physics, neuroscience, language modeling, and natural language understanding.  More information, including DOE research reports, publications, and data collections about deep learning networks, is available in the DOE databases and related resources provided below.

Related Research Information in DOE Databases

For additional information, see the OSTI Catalogue of Collections.

Additional Resources

 

Visit the Science Showcase Archive     

 

 

 

 

Last updated on Wednesday 15 March 2017