520.776 Learning on Silicon
Silicon models of adaptive neural computation. Topics include
on-line learning architecture, on-chip and chip-in-the-loop learning,
support vector "machines" in silicon, analog and mixed-signal adaptive
VLSI circuits, and technology directions. Students in groups will
design and implement a learning machine on a chip fabricated through
the MOSIS foundry.
Instructor: Prof. Gert
Cauwenberghs, Barton 209/400B,
gert@jhu.edu
Time and location: Th 1:30-4, Barton 225
Schedule
References
Books
Learning on
Silicon-- Adaptive VLSI Neural Systems, G. Cauwenberghs
and M. Bayoumi, Eds., Norwell MA: Kluwer Academic, 1999.
Adaptive Analog VLSI Neural Systems, M.A. Jabri,
R.J. Coggins and B.G. Flower, Chapman Hall, 1996.
Analog VLSI and Neural Systems, C.A. Mead,
Reading MA: Addison-Wesley, 1989.
Articles
"Neuromorphic
Learning VLSI Systems: A Survey," G. Cauwenberghs, in
T.S. Lande, Ed., Neuromorphic Systems Engineering, Norwell
MA: Kluwer Academic, 1998.
"Analog
VLSI Stochastic Perturbative Learning Architectures,"
G. Cauwenberghs, in T.S. Lande, Ed., Neuromorphic Systems
Engineering, Norwell MA: Kluwer Academic, 1998.
"Silicon
Support Vector Machine with On-Line Learning," R. Genov,
S. Chakrabartty and G. Cauwenberghs, Int. J. Pattern
Recognition and Artificial Intelligence,
vol. 17 (3), pp. 385-404, 2003.
"Kerneltron:
Support Vector Machine in Silicon," R. Genov and
G. Cauwenberghs, IEEE Trans. Neural Networks,
vol. 14 (5), pp. 1426-1434, 2003.
"Mixed-Signal
Real-Time Adaptive Blind Source Separation," A. Celik,
M. Stanacevic and G. Cauwenberghs, Proc. IEEE
Int. Symp. Circuits and Systems (ISCAS'2004), Vancouver Canada,
May 23-26, 2004.
"Micropower
Mixed-Signal Acoustic Localizer," M. Stanacevic and
G. Cauwenberghs, Proc. IEEE Eur. Solid State Circuits
Conf. (ESSCIRC 2003), Estoril Portugal, Sept. 16-18, 2003.
"Spike
Timing-Dependent Plasticity in the Address Domain,"
R.J. Vogelstein, F. Tenore, R. Philipp,
M.S. Adlerstein, D.H. Goldberg, and G. Cauwenberghs,
Adv. Neural Information Processing Systems (NIPS'2002),
Cambridge: MIT Press, vol. 15, 2003.
"Probabilistic
Synaptic Weighting in a Reconfigurable Network of VLSI
Integrate-and-Fire Neurons," D.H. Goldberg,
G. Cauwenberghs and A.G. Andreou, Neural Networks,
vol. 14 (6-7), pp. 781-793, Aug. 2001.
"AdOpt:
Analog VLSI Stochastic Optimization for Adaptive Optics,"
M. Cohen, R.T. Edwards, G. Cauwenberghs,
M. Vorontsov and G. Carhart, Proc. Int. Joint
Conf. Neural Networks (IJCNN'99), Washington DC, vol. 4,
pp. 2343-2346, 1999.
Gert Cauwenberghs
January 29, 2004