Professor
Biosystems, Data Science
410 ECE
Campus Box 352500
University of Washington
Seattle, WA 98195
Phone: 206-685-1315
Email: atlas@ece.uw.edu
Research Web Page: sites.google.com/a/uw.edu/isdl
Biography
Les Atlas joined UW Electrical & Computer Engineering as an assistant professor in 1984 at the University of Washington. He has been a leader in signal processing research and educational activity in the Pacific Northwest, co-chairing the IEEE International Conference on Acoustics, Speech, and Signal Processing in 1998 with Xuedong Huang of Microsoft.
Atlas’ research has had an impact on signal processing for dynamical systems, time-frequency analysis and nonstationary statistics, with applications in streaming data, acoustics, machine monitoring, sensor arrays, speech processing and auditory sciences. His publication "Improving Generalization with Active Learning" initiated the machine learning area of active learning. His earlier work: "Training Connectionist Networks with Queries and Selective Sampling," was the first on selective sampling, and continues to have impact in machine learning.
Atlas’ graduate students have also had tremendous impact — such as the first publication on trained (linear) convolutional neural networks for temporal signals, securing top faculty positions, initiating machine learning at Google, receiving multiple Technical Emmy Awards and founding companies such as Redfin.
Atlas’ recent and current research is funded by the Army Research Office, the Office of Naval Research and the Wallace H. Coulter Foundation.
Awards and Honors
Research Projects
Recent Publications
- S. Wisdom, T. Powers, J. Hershey, J. Le Roux, L. Atlas, "Full Capacity Unitary recurrent Neural Networks," Proc. NIPS 2016. [ Link ]
- D Cohn, L Atlas, and R Ladner, “Improving generalization with active learning,” Machine learning 15 (2), pp. 201-221, 1994.
- S. Wisdom, G. Okopal, L. Atlas, and J. Pitton, “Voice Activity Detection Using Subband Noncircularity,” Proc. IEEE ICASSP, Brisbane, Austrailia, April 2015. T Homma, L Atlas, and R Marks, “An Artificial Neural Network for Spatio-Temporal Bipolar Patters: Application to Phoneme Classification,” Advances in Neural Information Processing Systems 1: 31–40, 1988.
- S. Wisdom, T. Powers, L. Atlas, and J. Pitton, “Enhancement and Recognition of Reverberant and Noisy Speech by Extending Its Coherence,” arXiv:1509.00533, Sep. 2015.
- G. Okopal, S. Wisdom, and L. Atlas, “Speech Analysis with the Strong Uncorrelating Transform,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 23, no. 11, pp. 1858–1868, Nov. 2015.
- B. Ekin, L. Atlas, M. Mirbagheri, and A. Lee, "An Alternative Approach for Auditory Attention Tracking Using Single-Trial EEG,” Proc. IEEE ICASSP, Shanghai, China, March 2016.