BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Can machine learning trump theory in communication system design? 
 - Prof. Andrea Goldsmith\, Stanford
DTSTART:20190510T110000Z
DTEND:20190510T120000Z
UID:TALK119197@talks.cam.ac.uk
CONTACT:Prof. Ramji Venkataramanan
DESCRIPTION: Design and analysis of communication systems have traditional
 ly relied on mathematical and statistical channel models that describe how
  a signal is corrupted during transmission. In particular\, communication 
 techniques such as modulation\, coding and detection that mitigate perform
 ance degradation due to channel impairments are based on such channel mode
 ls and\, in some cases\, instantaneous channel state information about the
  model. However\, there are propagation environments where this approach d
 oes not work well because the underlying physical channel is too complicat
 ed\, poorly understood\, or rapidly time-varying. In these scenarios we pr
 opose a completely new approach to communication system design based on ma
 chine learning (ML). In this approach\, the design of a particular compone
 nt of the communication system (e.g. the coding strategy or the detection 
 algorithm) utilizes tools from ML to learn and refine the design directly 
 from training data. The training data that is used in this ML approach can
  be generated through models\, simulations\, or field measurements. We pre
 sent results for three communication design problems where the ML approach
  results in better performance than current state-of-the-art techniques: s
 ignal detection without accurate channel state information\, signal detect
 ion without a mathematical channel model\, and joint source-channel coding
  of text. Broader application of ML to communication system design in gene
 ral and to millimeter wave and molecular communication systems in particul
 ar is also discussed.\n\n\n\n*BIO*:  Andrea Goldsmith is the Stephen Harri
 s professor in the School of Engineering and a professor of Electrical Eng
 ineering at Stanford University. Her research interests are in information
  theory and communication theory\, and their application to wireless commu
 nications and related fields. Prof. Goldsmith has received several awards 
 for her work\, including the IEEE ComSoc Edwin H. Armstrong Achievement Aw
 ard as well as Technical Achievement Awards in Communications Theory and i
 n Wireless Communications\, the National Academy of Engineering Gilbreth L
 ecture Award\, and the IEEE ComSoc and Information Theory Society Joint Pa
 per Award. She is author of the book ``Wireless Communications'' and co-au
 thor of the books ``MIMO Wireless Communications'' and “Principles of Co
 gnitive Radio\,” all published by Cambridge University Press\, as well a
 s an inventor on 28 patents.  She co-founded and served as Chief Technical
  Officer of Plume WiFi (formerly Accelera\, Inc.) and of Quantenna (QTNA)\
 , Inc. She has also held industry positions at Maxim Technologies\, Memory
 link Corporation\, and AT&T Bell Laboratories \, and currently chairs the 
 Technical Advisory Boards of Interdigital Corp.\, Quantenna Communications
 \, Cohere Communications\, and Sequans.  Prof. Goldsmith is a member of th
 e National Academy of Engineering and the American Academy of Arts and Sci
 ences\, a Fellow of the IEEE and of Stanford.
LOCATION:Department of Engineering - LT2
END:VEVENT
END:VCALENDAR