MIL - The University of Tennessee
the university of tennessee machine intelligence lab
  
Andrew Davis, M.S. student
  
Machine Intelligence Lab
630 Min H. Kao Building
The University of Tennessee
Knoxville, TN 37996-2100

  
Research Deep Learning Architectures 
  
  Deep machine learning algorithms and architectures
  Visualizing and interpreting representations learned by deep architectures is becoming a key challenge. My work pertains to addressing these issues in the context of DeSTIN. I also study efficient GPU implementations of DeSTIN for broad application domains.
  
Selected Publications
  
[1]     A. Davis, I. Arel, "Low-Rank Approximations for Conditional Feedforward Computation in Deep Neural Networks," Workshop paper in the Workshop Proceedings of the International Conference on Learning Representations (ICLR) 2014, Banff, Canada, April, 2014 [pdf]
[2]     S. Young, I. Arel, A. Davis, A. Mishtal, "Hierarchical Spatiotemporal Feature Extraction using Recurrent Online Clustering," Pattern Recognition Letters, February, 2014 [pdf]
[3]     A. Davis, I. Arel, "On the Episode Duration Distribution Spanning Arbitrary States in Fixed-Policy Markov Decision Processes," in Proc. of the 23rd Florida Artificial Intelligence Research Society Conference (FLAIRS-23) , May, 2010 [pdf]
[4]     S. Anuradha Bulusu, I. Arel, B. Arazi, A. Davis, G. Bitar, "A Data Security Protocol for the Trusted Truck System," in Proc. 6th Annual Cyber Security and Information Intelligence Research Workshop, Oak Ridge National Lab, Oak Ridge, TN, April, 2010 [pdf]