soft computing colloquium 2 selection of neural network, hybrid neural networks

21
Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks.

Upload: conrad-jacobs

Post on 16-Jan-2016

233 views

Category:

Documents


1 download

TRANSCRIPT

Page 1: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

Soft Computing

Colloquium 2

Selection of neural network,

Hybrid neural networks.

Page 2: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 2

Objectives

• Why too much of models of neural networks (NN)?

• Classes of tasks and classes of NN

• Hybrid neural networks

• Hybrid model based on MLP and ART-2

• Paths to improvement of neural networks

Page 3: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 3

Submit a questions to discuss

• Paths to improvement of neural networks:– Development of growth neural networks with

feedback and delays– Development of theory of spiking neurons and

building of associative memory based on its– Development of neural network in which

during learning logical (verbal) inference would appearance from associative memory

Page 4: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 4

Why too much of models of neural networks (NN)?

Models of neural networkssimulate separate aspectsof working of brain (e.g. associative memory, buthow it works in whole isunknown for us.Questions:1) What is consciousness?2) What is role of emotions?3) How different areas ofbrain are coordinated?4) How associative linksare transformed and used inlogical inference and calculations?

Page 5: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 5

Page 6: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 6

Classes of tasks :

• prediction

• classification

• data association

• data conceptualization

• data filtering

• Neuromathematics

Page 7: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 7

Classes of Neural Networks:• Multi Layer Networks

– Multi Layer Perceptron (MLP)• Supervised learning

– Radial Basis Functions (RBF-networks)

• Supervised learning– Recurrent Neural Networks

(Elman, Jordan)• Supervised learning• Reinforcement learning

– Counterpropagation network• Supervised learning

• One-layer networks– Self-organized map (MAP)

• Unsupervised learning– Artificial resonance theory

(ART)• Unsupervised learning

– Hamming network• Supervised learning

• Fully interconnected networks– Hopfield network

• Supervised learning– Boltzmann machine

• Supervised learning– Bi-directional associative

memory• Supervised learning

• Spiking networks• Supervised learning• Unsupervised learning• Reinforcement learning

Page 8: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 8

Counterpropagation network

Page 9: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 9

Network Selector Table

Page 10: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 10

Hybrid Neural Networks.• Includes:

– Main neural network– Other neural network

• Preprocessing• Postprocessing

• Some models of neural networks consist of some layers working by different manner and so such neural networks may be viewed as hybrid neural networks (including more elementary networks)

• Some authors calls hybrid neural networks such model which combine paradigms of neural networks and knowledge engineering.

Page 11: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 11

Hybrid Neural Network based on models of Multi-Layer Perceptron and Adaptive Resonance Theory (A.Gavrilov, 2005)

• Aims to keep capabilities of ARM (plasticity and stability)

• Include in ART capabilities of MLP during learning to obtain complex secondary features from primary features (to approximate any function)

Page 12: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 12

Disadvantages of model ART-2 for recognition of images

• It uses of metrics of primary features of images to recognize of class or create of new class,

• Transformations of graphic images (shift or rotation or others) essentially influence on distance between input vectors

• So it is unsuitable for control system of a mobile robots

Page 13: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 13

Architecture of hybrid neural networkoutput vector

output layer:clusters

input layer:input variables

y1 y2 ym

input layer ofART-2, output

layer of perceptron

hidden layer ofperceptron

input vector

x1 x2 xn

Page 14: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 14

Algorithm of learning without teacher

• Set of initial weights of neurons; Nout:=0;

• Input of image-example and calculate of outputs of perceptron;

• If Nout=0 then forming of new cluster-output neuron;

• If Nout>0 then calculate of distances between weight vector of ART-2 and output vector of perceptron, select of minimum of them (selection of output neuron-winner) and decide to create or not new cluster;

• If new cluster is not created then calculate new values of weights of output neuron-winner and calculate new weights of perceptron with algorithm “error back propagation”.

Page 15: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 15

The illustration of algorithm

1 3

4 2

5

R1

Page 16: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 16

Images and parameters used in experiments

Quantity of input neurons (pixels) - 10000 (100х100),Quantity of neurons in hidden layer of perceptron - 20,Quantity of output neurons of perceptron (in input layer of ART-2) Nout - 10,Radius of cluster R was used in experiments in different manners:

1) adapt and fix,2) calculate for every image by formulas S/(2Nout),

where S – average input signal, Nout – number of output neurons of perceptron,3) calculated as 2Dmin,where Dmin – minimal distance between input vector of ART2 and weight vectors in previous image.Activation function of neurons of perceptron is rational sigmoid with parameter a=1,Value of learning step of perceptron is 1,Number of iterations of recalculation of weights of perceptron is from 1 to 10.

1) 2) 3)

Page 17: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 17

Series of images 1

Page 18: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 18

Program for experiments

Page 19: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 19

For sequence of images of series 1, 2, 1, 2 (a dark points are corresponding to 2nd kind of calculation

of vigilance and light – to 1st one).

Number of recognized cluster

02468

1012141618

1 4 7 10 13 16 19 22 25 28 31 34 37 40 43 46 49 52 55 58 61

image

nu

mb

er

Page 20: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 20

For sequence of images of series 1 at different

number of iteration of EBP algorithm: 1, 3, 5, 7, 9.

Distance between output vector of MLP and centroid of recognized cluster

0

0,001

0,002

0,003

0,004

1 2 3 4 5 6 7 8 9

image

Dis

tan

ce

Page 21: Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks

14.11.2005 21

Paths to improvement of neural networks

• Development of growth neural networks with feedback and delays

• Development of theory of spiking neural networks and building of associative memory based on them

• Development of neural network in which during learning logical (verbal) inference would appearance from associative memory