MIL - The University of Tennessee
the university of tennessee machine intelligence lab
Tom Karnowski, Ph.D.
Machine Intelligence Lab
606 Min H. Kao Building
The University of Tennessee
Knoxville, TN 37996-2100

Research Deep Learning Architectures 
  Deep machine learning algorithms and architectures
  I have studied deep machine learning systems that utilize non-linear function approximation techniques to scale and improve convergence properties. In particular, I pioneered work on the DeSTIN architecture. Applications for this technology include robust pattern recognition in high-dimensional spaces.
Selected Publications
[1]     T. Karnowski, I. Arel, S. Young, "Modeling Temporal Dynamics with Function Approximation in Deep Spatio-Temporal Inference Network," in Proc. 2nd International Conference on Biologically Inspired Cognitive Architectures (BICA), November, 2011 [pdf]
[2]     T. Karnowski, I. Arel, D. Rose, "Deep Spatiotemporal Feature Learning with Application to Image Classification," The 9th International Conference on Machine Learning and Applications (ICMLA'10), December, 2010 [pdf]
[3]     I. Arel, D. Rose, T. Karnowski, "Deep Machine Learning - A New Frontier in Artificial Intelligence Research," IEEE Computational Intelligence Magazine, Vol. 14, pp. 12-18, November, 2010 [pdf]
[4]     D. Rose, I. Arel, T. Karnowski, V. Paquit, "Applying Deep-Layered Clustering to Mammography Image Analytics," in Proc. of the Annual ORNL Biomedical Science and Engineering Conference (BSEC) 2010, May, 2010 [pdf]
[5]     S. Young, I. Arel, T. Karnowski, D. Rose, "A Fast and Stable Incremental Clustering Algorithm," in Proc. 7th International Conference on Information Technology (ITNG), April, 2010 [pdf]
[6]     I. Arel, D. Rose, T. Karnowski, "A Deep Learning Architecture Comprising Homogeneous Cortical Circuits for Scalable Spatiotemporal Pattern Inference," in Proc. NIPS 2009 Workshop on Deep Learning for Speech Recognition and Related Applications , December, 2009 [pdf]