The National Academies Logo
Research Associateship Programs
Fellowships Office
Policy and Global Affairs

Participating Agencies - NRL

  Sign InPrintable View

Opportunity at Naval Research Laboratory (NRL)

Deep Learning Postdoctoral Research


Naval Research Laboratory, DC, Information Technology

RO# Location
64.15.18.B8506 Washington, DC 203755321


Name E-mail Phone
Smith, Leslie Neil 202.767.9532


We are seeking an excellent postdoctoral researcher in machine learning, computer science, applied mathematics, physics, or a related field, to work closely with us on a few projects, plus pursuing your own novel lines of research. Our research involves basic, practical, and applied research, development, and evaluation of innovative deep learning methodologies. Our current research foci include deep convolutional networks, deep reinforcement learning for decision making, and combining machine learning with artificial intelligence. Some of our current projects include reducing the need for large labeled training datasets, novelty detection (i.e., enabling a neural network to say "I don't know"), one shot learning, a disciplined approach to setting hyper-parameters, data augmentation in feature space, making DL explainable, and the use of new types of loss functions within networks. Expertise gained from this fundamental deep learning research is utilized to support Navy applications that often guide us to new research avenues. Anticipated future projects include the use of deep reinforcement learning for decision making, physics-based deep learning architectures, methods to improve the ability of deep networks to generalize, and the use of GANs for generating novel experiences for training deep reinforcement learning networks. We enjoy close ties with academia, the military, and other customers who can benefit from the prototypes that we develop. Our group often includes summer interns, postdoctoral and visiting summer researchers.


Selected References:

Smith, Leslie N., and Nicholay Topin. "Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates." arXiv preprint arXiv:1708.07120 (2017).

Smith, Leslie N. "Best Practices for Applying Deep Learning to Novel Applications." arXiv preprint arXiv:1704.01568 (2017).

Smith, Leslie N. "Cyclical learning rates for training neural networks." In Applications of Computer Vision (WACV), 2017 IEEE Winter Conference on, pp. 464-472. IEEE, 2017.


Deep Learning; Machine Learning; Artificial Intelligence; Computer Vision; Decision Aids; Anomaly Detection


Citizenship:  Open to U.S. citizens and permanent residents
Level:  Open to Postdoctoral applicants
Copyright © 2014. National Academy of Sciences. All rights reserved. 500 Fifth St. N.W., Washington, D.C. 20001.
Terms of Use and Privacy Statement.