21 Dec, 2018 (Fri)Time:
SpeakerProf. Eli Yablonovitch
Electrical Engineering and Computer Sciences Dept.
University of California
About seventy years ago, analog computing was regarded as having equal prospects as digital computing. Operational amplifiers could provide analog differentiation and integration functions. Nonetheless analog computing disappeared, being unable to provide the precision and dynamic range required for solving real problems.
The emergence of Deep Learning has been accompanied by the realization that only modest precision is sufficient for the inference step. This has taken us from regular Floating Point, to half-precision (16 bits), to quarter-precision, and with some difficulty even single-bit precision. The race is on for specialized hardware accelerators, whose acronyms have transitioned from CPU®GPU®TPU®IPU. For example, 8-bit precision analog can provide analog matrix multiplication in Deep Learning accelerators, which is now being pursued commercially.
I will examine three different potential forms of analog computing.
- analog matrix multipliers for Deep Learning.
- analog, not digital simulated annealing for solving Ising type problems.
- adiabatic computing, (classical not quantum), also for solving Ising type optimizations.
One of the limitations for Ising problems is that the analog couplings demand precision that grows with problem size. It appears that, already at 1% analog precision, interesting Ising problems can be addressed.
Biography of the speaker:
Prof. Yablonovitch introduced the idea that strained semiconductor lasers could have superior performance due to reduced valence band (hole) effective mass. With almost every human interaction with the internet, optical telecommunication occurs by strained semiconductor lasers.
He is regarded as a Father of the Photonic BandGap concept, and he coined the term “Photonic Crystal”. The geometrical structure of the first experimentally realized Photonic bandgap, is sometimes called “Yablonovite”.
In his photovoltaic research, Yablonovitch introduced the 4(n squared) (“Yablonovitch Limit”) light-trapping factor that is in worldwide use, for almost all commercial solar panels.
His mantra that “a great solar cell also needs to be a great LED”, is the basis of the world record solar cells: single-junction 28.9% efficiency; dual-junction 31.5%; quadruple-junction 38.8% efficiency; all at 1 sun.
All are welcome.
OrganizerProf. V.O.K. Li
Most seminars are open to the general public, free of charge, unless otherwise stated. Registration is not required. Arrangement for car parking facilities on campus please contact us for details.
For enquiries, please contact:
Department of Electrical and Electronic Engineering,
Room 601, Chow Yei Ching Building,
Pokfulam Road, Hong Kong
Tel: (852) 2859 7093