TITLE: Deep Neural Networks from a Developmental Perspective

ABSTRACT:

There is a recent surge in research activities around the idea of the so-called “deep neural networks” (DNN). As a technical item, DNN without a doubt is an important classroom topic and several tutorial articles and related learning resources are available. Nonetheless, streams of questions about DNN never subside from students or researchers and there appears to be a frustrating tendency among the learners to treat DNN simply as a black box. In this talk, a pedagogy is attempted with the aim to present DNN in the well-established traditional pattern recognition framework so that a deeper understanding of DNN can be reached through proper contrast to conventional techniques. Furthermore, the structure of DNN is in essence no different from a conventional feedforward neural network or multilayer perceptron, a fact that often triggers the perplexing question why it took sixty years to get to what it is today. In particular, we review the developmental aspect of DNN, in terms of how advances in connectionist models have evolved into this powerful technique. Time permitting, we’ll discuss the application of DNN in the area of automatic speech recognition so as to ascertain its efficacy, as compared to traditional statistical modeling, and to bring to surface possibly unrealized potentials of DNN as well as conventional techniques.

BIO: Biing-Hwang (Fred) Juang is the Motorola Foundation Chair Professor and a Georgia Research Alliance Eminent Scholar at Georgia Institute of Technology. He is also enlisted as Honorary Chair Professor at several renowned universities. He received a Ph.D. degree from University of California, Santa Barbara. He had conducted research work at Speech Communications Research Laboratory (SCRL) and Signal Technology, Inc. (STI) in the late 1970s on a number of Government-sponsored research projects and at Bell Labs during the 80s and 90s until he joined Georgia Tech in 2002. Prof. Juang’s notable accomplishments include development of vector quantization for voice applications, voice coders at extremely low bit rates (800 bps and ~300 bps), robust vocoders for satellite communications, fundamental algorithms in signal modeling for automatic speech recognition, mixture hidden Markov models, discriminative methods in pattern recognition and machine learning, stereo- and multi-phonic teleconferencing, and a number of voice-enabled interactive communication services. He was Director of Acoustics and Speech Research at Bell Labs (1996-2001).

Prof. Juang has published extensively, including the book “Fundamentals of Speech Recognition”, co-authored with L.R. Rabiner, and holds nearly two dozen patents. He received the Technical Achievement Award from the IEEE Signal Processing Society in 1998 for contributions to the field of speech processing and communications and the Third Millennium Medal from the IEEE in 2000. He also received two Best Senior Paper Awards, in 1993 and 1994 respectively, and a Best Paper Awards in 1994, from the IEEE Signal Processing Society. He served as the Editor-in-Chief of the IEEE Transactions on Speech and Audio Processing from 1996 to 2002. He was elected an IEEE Fellow (1991), a Bell Labs Fellow (1999), a member of the US National Academy of Engineering (2004), and an Academician of the Academia Sinica (2006). He was named recipient of the IEEE Field Award in Audio, Speech and Acoustics, the J.L. Flanagan Medal, and a Charter Fellow of the National Academy of Inventors (NAI), in 2014