Postdoc and Graduate Studies

[Soo-Young Lee]

Subject: Postdoc/Graduate Study - Neural Net Applications and Implementation
From:    "Soo-Young Lee" <sylee at ee.kaist.ac.kr>

               POSTDOCTORAL POSITION / GRADUATE STUDENTS
               Computation and Neural Systems Laboratory
                 Department of Electrical Engineering
          Korea Advanced Institute of Science and Technology

A postdoctoral position is available beginning after March 1st, 1994. The
position is for one year initially, and may be extended for another year.  
Graduate students with full scholarship are also welcome, especially
from developing countries. 

We are seeking individuals interested in researches on neural net applications
and/or VLSI implementation.  Especially we emphasizes "systems" approach,
which combines neural network theory, application-specific knowledge, and
hardware implementation technology for much better perofrmance.  Although
many applications are currently investigated, speech recognition is the
preferred choice at this moment.

Interested parties should send a C.V. and a brief statement of research
interests to the address listed below.

Present address:

	Prof. Soo-Young Lee
	Computation and Neural Systems Laboratory
	Department of Electrical Engineering
	Korea Advanced Institute of Science and Technology
	373-1 Kusong-dong, Yusong-gu
	Taejon 305-701
	Korea (South)
	Fax: +82-42-869-3410
	E-mail: sylee at ee.kaist.ac.kr

                RESEARCH INTERESTS OF THE GROUP

The Korea Advanced Institute of Science and Technology (KAIST) is an unique
engineering school, which emphasies graduate studies through high-quality
researches.  All graduate students receive full scholarship, and Ph.D.
course students are free from military services.  The Department of Electrical
Engineering is the largest one with 39 professors, 250 Ph.D. course students,
180 Master course students, and 300 undergraduate students.  The Computation
and Neural Systems Laboratory is lead by Prof. Soo-Young Lee, and consists
of about 10 Ph.D. course students and about 5 Master course students.

The primary focus of this laboratory is to merge neural network theory,
VLSI implementation technology, and application-specific knowledge for much 
better performance at real world applications.  Speech recognition,
pattern recognition, and control applications have been emphasized.
Neural network models develpoed include Multilayer Bidirectional Associative
Memoryas an extention of BAM into multilayer architecture, IJNN (Intelligent 
Judge Neural Networks) for intelligent ruling verdict for disputes from
several low-level classifiers, TAG (Training by Adaptive Gain) for large-scale
implementation and speaker adaptation, and Hybrid Hebbian-Backpropagation
Algorithm for MLP for improved robustness and generalization.  The correlation
matrix MBAM chip had been fabricated, and new on-chip learning analog
neuro-chip is under design now.