Neural Networks with Anticipation: Problems and Prospects

20
NEURAL NETWORKS WITH ANTICIPATION: PROBLEMS AND PROSPECTS Alexander MAKARENKO Institute for Applied System Analysis at National Technical University of Ukraine (KPI)

description

AACIMP 2010 Summer School lecture by Alexander Makarenko. "Applied Mathematics" stream. "General Tasks and Problems of Modelling of Social Systems. Problems and Models in Sustainable Development" course. Part 6.More info at http://summerschool.ssa.org.ua

Transcript of Neural Networks with Anticipation: Problems and Prospects

Page 1: Neural Networks with Anticipation: Problems and Prospects

NEURAL NETWORKS WITH

ANTICIPATION:

PROBLEMS AND

PROSPECTS

Alexander MAKARENKO

Institute for Applied System Analysis at

National Technical University of Ukraine (KPI)

Page 2: Neural Networks with Anticipation: Problems and Prospects

INTRODUCTION

Nonlinear networks science

(problems and effects):

stability

bifurcations

chaos

sinchronisation

turbulence

chimera states

Page 3: Neural Networks with Anticipation: Problems and Prospects

MODELS AND SYSTEMS

(RECENTLY):coupled oscillators

coupled maps

neural networks

cellular automata

o.d.e. system

………MAINLY of NEUTRAL or

WITH DELAY

Page 4: Neural Networks with Anticipation: Problems and Prospects

ANTICIPATION

Neural network learning (Sutton, Barto, 1982)

Control theory (Pyragas, 2000?)

Neuroscience (1970-1980,… , 2009)

Traffic investigations and models (1980, …, 2008)

Biology (R. Rosen, 1950- 60- ….)

Informatics, physics, cellular automata, etc. (D. Dubois, 1982 - ….)

Models of society (Makarenko, 1998 - …)

Page 5: Neural Networks with Anticipation: Problems and Prospects

ANTICIPATION

The anticipation property is that the individual makes a decision accounting the future states of the system [1].

One of the consequences is that the accounting for an anticipatory property leads to advanced mathematical models. Since 1992 starting from cellular automata the incursive relation had been introduced by D. Dubois for the case when

„the values of of state X(t+1) at time t+1 depends on values X(t-i) at time t-i, i=1,2,…, the value X(t) at time t and the value X(t+j) at time t+j, j=1,2,… as the function of command vector p‟ [1].

Page 6: Neural Networks with Anticipation: Problems and Prospects

ANTICIPATION In the simplest cases of discrete systems this

leads to the formal dynamic equations (for the case of discrete time t=0, 1, ..., n, ... and finite number of elements M):

where R is the set of external parameters (environment, control), {si(t)} the state of the system at a moment of time t (i=1, 2, …, M), g(i) horizon of forecasting, {G} set of nonlinear functions for evolution of the elements states.

( 1) ({ ( )},...,{ ( ( ))}, ),i i i is t G s t s t g i R

Page 7: Neural Networks with Anticipation: Problems and Prospects

“In the same way, the hyperincursion is an

extension of the hyper recursion in which several

different solutions can be generated at each time

step” [1, p.98].

According [1] the anticipation may be of „weak‟ type

(with predictive model for future states of system,

the case which had been considered by R. Rosen)

and of „strong‟ type when the system cannot make

predictions.

Page 8: Neural Networks with Anticipation: Problems and Prospects

HOPFIELD TYPE NETWORK

WITH ANTICIPATION

Page 9: Neural Networks with Anticipation: Problems and Prospects

SOME EXAMPLES OF

MODELS

( 1) ( ) ( 1)j ji i ji ix n f w x n w x n

N

i

iji

N

i

ijij nxwnxwfnx11

)1()()1()1(

Page 10: Neural Networks with Anticipation: Problems and Prospects

EXAMPLE OF ACTIVATION

FUNCTION

0, 0

( ) , [0,1)

1, 1

якщо x

f x x якщо x

якщо x

Page 11: Neural Networks with Anticipation: Problems and Prospects

Network with 2 coupled neurons

Single-valued periodicity

Page 12: Neural Networks with Anticipation: Problems and Prospects

Neuronert with 2 neuroons

Multi-valued ciclicity

-0,2

0

0,2

0,4

0,6

0,8

1

1,2

-0,2 0 0,2 0,4 0,6 0,8 1 1,2

1 нейрон

2 н

ей

ро

н

Page 13: Neural Networks with Anticipation: Problems and Prospects

Netework with 6 neurons. Ciclicity

Page 14: Neural Networks with Anticipation: Problems and Prospects

Network with 8 neurons

Page 15: Neural Networks with Anticipation: Problems and Prospects

The influence on anticipation

parameter

Page 16: Neural Networks with Anticipation: Problems and Prospects

PROBLEMS AND PROSPECTS

Page 17: Neural Networks with Anticipation: Problems and Prospects

RESEARCH DIRECTIONS

I. General investigations of abstract mathematical objects:

Definitions of regimes:

Periodicity;

Chaos;

Solitons;

Chimera states;

Bifurcations;

Attractors;

Etc.

Page 18: Neural Networks with Anticipation: Problems and Prospects

RESEARCH DIRECTIONS

II. Investigation of concrete models and solutions

In artificial neural networks

In cellular automata

In coupled maps

Solitons, traveling waves

Self-organization

Collapses

Etc.

Page 19: Neural Networks with Anticipation: Problems and Prospects

RESEARCH DIRECTIONS

III. Interpretations and applications

Traffic modeling

Crowds movement

Socio- economical systems

Control applications

Neuroscience

Conscious problem

Physics

IT

Page 20: Neural Networks with Anticipation: Problems and Prospects

REFERENCES

1. Dubois D. Generation of fractals from incursive automata, digital

diffusion and wave equation systems. BioSystems, 43 (1997) 97-114.

2 Makarenko A., Goldengorin B. , Krushinski D. Game „Life‟ with

Anticipation Property. Proceed. ACRI 2008, Lecture Notes Computer

Science, N. 5191, Springer, Berlin-Heidelberg, 2008. p. 77-82

3. B. Goldengorin, D.Krushinski, A. Makarenko Synchronization of Movement for Large – Scale Crowd. In: Recent Advances in Nonlinear

Dynamics and Synchronization: Theory and applications. Eds. Kyamakya

K., Halang W.A., Unger H., Chedjou J.C., Rulkov N.F.. Li Z., Springer, Berlin/Heidelberg, 2009 277 – 303

4. Makarenko A., Stashenko A. (2006) Some two- steps discrete-time

anticipatory models with „boiling‟ multivaluedness. AIP Conference

Proceedings, vol.839, ed. Daniel M. Dubois, USA, pp.265-272.