| |
 Programme
Overview
Detailed
Programme
| Neural Networks
Theory II (NNTII) |
CHAIR: BARTLOMIEJ BELICZYNSKI
Time: Monday 21st
March, 14h20-16h00
| NNTII-1 |
| |
| Title: |
|
|
Speeding up backpropagation with
Multiplicative Batch Update Step |
| Author(s): |
P. Cruz |
| Abstract: |
Updating steps in a backpropagation algorithm
presented by several authors for backpropagation algorithm.
The field of statistics Stochastic Approximation has a close
show that for functions of one variable, different values
of u and d can produce very different results: fast convergence
at the cost of a poor solution, slow convergence with a better
solution, or produce a fast move towards a solution but without
converging. To speed up backpropagation in a simple manner
we propose a batch step adaptation technique for the online
backpropagation algorithm based on theoretical results on
simple cases. |
 |
| NNTII-2 |
| |
| Title: |
|
|
Generating Sequential Triangle
Strips by Using Hopfield Nets |
| Author(s): |
Jiri Sima |
| Abstract: |
The important task of generating the minimum
number of sequential triangle strips(tristrips) for a given
triangulated surface model is motived by applications in computer
graphics. This hard combinatorial optimization problem is
reduced to the minimum energy problem in Hopfield nets by
a linear-size construction. The Hopfield network powered by
simulated annealing (i.e. Boltzmann machine) which is implemented
in a program HTGEN can be used for computing the semi-optimal
stripifications. Practical experiments confirm that one can
obtain much better results using HTGEN than by a leading stripification
program FTSG although the running time of simulated annealing
grows rapidly near the global optimum. |
|
| NNTII-3 |
| |
| Title: |
|
|
The Linear Approximation Method
to the Modified Hopfield Neural Network Parameters Analysis |
| Author(s): |
S. I. Bauk,
S. M. Perovich,
A. Lompar |
| Abstract: |
The dynamic of Hopfield network is usually described
by the system of linear differential equations. Our idea is
to modify Hopfield network in aim to allow its behavior description
by the system of exponential equations. Furthermore, the linear
approximation method to the system of exponential equations,
based on the Special Trans Function Theory (STFT), has been
discussed. |
|
| NNTII-4 |
| |
| Title: |
|
|
The Analytical Analysis of Hopfield
Neuron Parameters by the Application of Special Trans Function
Theory |
| Author(s): |
S. M. Perovich,
S. I. Bauk,
N. Konjevic |
| Abstract: |
The subject of the theoretical analysis presented
in the paper is Hopfield neuron electronic model modification
based upon capacitor replacement with an inverse polarized
diode. The modified neuron parameters have been analytically
analyzed by application of the Special Trans Function Theory
(STFT). The obtained results are presented numerically and
graphically. |
|
| NNTII-5 |
| |
| Title: |
|
|
Time-Oriented Hierarchical Method
for Computation of Minor Components |
| Author(s): |
M. Jankovic,
H. Ogawa |
| Abstract: |
This paper proposes a general method that transforms
known neural network MSA algorithms, into MCA algorithms.
The method uses two distinct time scales. A given MSA algorithm
is responsible, on a faster time scale, for the “behavior”
of all output neurons. At this scale minor subspace is obtained.
On a slower time scale, output neurons compete to fulfill
their “own interests”. At this scale, basis vectors
in the minor subspace are rotated toward the minor eigenvectors.
Actually, time-oriented hierarchical method is proposed. Some
simplified mathematical analysis as well as simulation results
are presented. |
|