Deep Learning and Its Applications to Signal and Information Processing

Since 2006, deep learning—a new area of machine learning research—has emerged impacting a wide range of signal and information processing work.

Various workshops, such as the 2009 ICML Workshop on Learning Feature Hierarchies; the 2008 NIPS Deep Learning Workshop: Foundations and Future Directions; and the 2009 NIPS Workshop on Deep Learning for Speech Recognition and Related Applications as well as an upcoming special issue on deep learning for speech and language processing in IEEE Transactions on Audio, Speech, and Language Processing (2010) have been devoted exclusively to deep learning and its applications to classical signal processing areas. We have also seen the government sponsor research on deep learning (e.g., the DARPA deep learning program).

To learn more about emerging technology enabled by deep learning, the current research conducted in this area, and the possible future research directions, the readers can refer to the column article entitled “Deep Learning and Its Applications to Signal and Information Processing” in the January issue of IEEE Signal Processing Magazine.