MIL - The University of Tennessee
the university of tennessee machine intelligence lab
Steven Young, Ph.D. - Post-doc @ Oak Ridge National Laboratory
[ cv
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
  Online (or incremental) clustering is at the core of the Deep Spatiotemporal Inference Network (DeSTIN) architecture - a deep learning architecture developed at our lab. I worked on enhancing the framework as well as improving its convergence and stability properties. Of particular focus is capturing temporal dependencies that span different time scales in DeSTIN.
Selected Publications
[1]     J. Holleman, I. Arel, J. Lu, S. Young, "Analog Inference Circuits for Deep Learning," to appear in the 2015 IEEE Biomedical Circuits and Systems Conference (BioCAS), October, 2015 [pdf]
[2]     J. Lu, S. Young, I. Arel, J. Holleman, "A 1 TOPS/W Analog Deep Machine-Learning Engine with Floating-Gate Storage in 0.13 um CMOS," in IEEE Journal of Solid State Circuits, January, 2015 [pdf]
[3]     S. Young, J. Liu, I. Arel, J. Holleman, "On the Impact of Approximate Computation in an Analog DeSTIN Architecture," IEEE Transactions on Neural Networks and Learning Networks, Vol. 25, No. 5, pp. 934 - 946, May, 2014 [pdf]
[4]     J. Lu, S. Young, I. Arel, J. Holleman, "'A 1TOPS/W Analog Deep Machine Learning Engine with Floating-Gate Storage in 0.13um CMOS," in Proc. 2014 IEEE international Solid-State Circuits Conference (ISSCC), pp. 30-32, February, 2014 [pdf]
[5]     S. Young, I. Arel, A. Davis, A. Mishtal, "Hierarchical Spatiotemporal Feature Extraction using Recurrent Online Clustering," Pattern Recognition Letters, February, 2014 [pdf]
[6]     J. Lu, S. Young, I. Arel, J. Holleman, "An Analog Online Clustering Circuit in 130nm CMOS," in Proc. IEEE Asian Solid-State Circuits Conference, November, 2013 [pdf]
[7]     S. Young, I. Arel, "Recurrent Clustering for Unsupervised Feature Extraction with Application to Sequence Detection," in Proc. IEEE International Conference on Machine Learning and Applications (ICMLA), December, 2012 [pdf]
[8]     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]
[9]     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]
[10]     S. Young, I. Arel, O. Arazi, "Pi-PIFO: A Scalable Pipelined PIFO Memory Management Architecture," Proc. of the 10th IEEE International Conference on Telecommunications, June, 2009 [pdf]