AVardanyan

Information about AVardanyan

Published on October 12, 2007

Author: Shariyar

Source: authorstream.com

Content

Multivariate Methods of Data Analysis in Cosmic Ray Astrophysics A. Chilingarian, A. Vardanyan:  Multivariate Methods of Data Analysis in Cosmic Ray Astrophysics A. Chilingarian, A. Vardanyan Cosmic Ray Division, Yerevan Physics Institute, Armenia Topics:  Topics Main tasks to be solved in cosmic ray astrophysics Analysis methods Preprocessing and indication of the best parameters Neural Networks for the main data analysis Multi Start Random Search learning algorithm Training, Validation and Generalization errors Overtraining control Slide3:  Individual event weights Results of NN classification and estimation Examples of applications The MAGIC telescope for detecting  -rays from point sources:  The MAGIC telescope for detecting  -rays from point sources The MAKET-ANI installation for the registration of Extensive Air Showers:  The MAKET-ANI installation for the registration of Extensive Air Showers The development of an extensive air shower induced by primary cosmic ray particle in the atmosphere:  The development of an extensive air shower induced by primary cosmic ray particle in the atmosphere The Monte-Carlo Simulation is the key problem of any physical inference in indirect experiments:  The Monte-Carlo Simulation is the key problem of any physical inference in indirect experiments What tasks we want to solve measuring EAS characteristics?:  What tasks we want to solve measuring EAS characteristics? An inverse problem to be solved: Experimental data Simulated data ?,?(Ne,Nμ,Nh,S…)  E,A(Ne,Nμ,Nh,S…) Identification of primary particle type Estimation of primary particle energy Why Neural Networks?:  Why Neural Networks? Neural Networks belong to the general class of nonparametric methods that do not require any assumption about the parametric form of a statistical model they use Are appropriate technique for classification and estimation tasks Are able to treat multidimensional input data The Neural information techniques:  The Neural information techniques The central issue of Neural Networks is a bounded mapping of n-dimensional input to m-dimensional output: The functional form of is accumulated in -NN parameters (weights) during the NN training process. The NN training process consists in iterative processing of simulated events, The aim of the training process consists in finding that provides the minimum of error (quality) function: A Feed-Forward Neural Network:  A Feed-Forward Neural Network An example of the NN output distribution in case of classification task:  An example of the NN output distribution in case of classification task Common drawbacks in NN training process:  Common drawbacks in NN training process Training only one network can lead to the suboptimal generalization Insufficient training events and a risk of overtraining Multi start random search algorithm:  Multi start random search algorithm The Random search learning algorithm implements the following steps: The initial values of NN weights are chosen randomly from Gaussian distribution with =0 and 0.01 The random step in the multidimensional space of NN weights is performed from initial point to modify the weights, the alternation of weights is done according to: where is the NN weight vector at th iteration, is the step size, RNDM is a random number from [0,1] interval, and the term introduces and controls the degree of dependence of the random step value on the already achieved quality function Slide15:  The quality function  is calculated at each iteration by presenting all the training events to NN If i ≤ i-1 , then the vector is kept as new weights of NN and the next step is initializing from that point in space of NN weights, otherwise – return to the previous point is implemented and a new random step is performed. Multi start technique consists in training many Neural Nets starting from different initial weights and using different step size parameters, allowing to scan many points in the multidimensional space of NN weights Training and Validation errors, Overtraining control:  Training and Validation errors, Overtraining control An acceptable procedure to avoid the overtraining:  An acceptable procedure to avoid the overtraining after each successful iteration of the learning process the net error is calculated for the validation sample if the validation error is less than the one obtained at previous iteration, then the NN weights obtained at the current training iteration are memorized else, the NN weights obtained at the previous iteration are stored At the end of training process the weights which provide the minimal error on the validation sample are found and used as the final best weights for NN The multi start RS technique provides a possibility to select the NN with best performance on the control data set:  The multi start RS technique provides a possibility to select the NN with best performance on the control data set Results of energy estimation by NN:  Results of energy estimation by NN Results of mass classification by NN:  Results of mass classification by NN Application of NN for gamma/hadron separation task in gamma-ray astronomy:  Application of NN for gamma/hadron separation task in gamma-ray astronomy Cosmic Ray differential energy spectra obtained by NN classification and estimation:  Cosmic Ray differential energy spectra obtained by NN classification and estimation

Related presentations


Other presentations created by Shariyar

Dr Chalmers
19. 10. 2007
0 views

Dr Chalmers

lect24 projections 1
01. 11. 2007
0 views

lect24 projections 1

PA04 What is News
08. 10. 2007
0 views

PA04 What is News

cisc geneva info
15. 10. 2007
0 views

cisc geneva info

SemkovaSpacerad1
15. 10. 2007
0 views

SemkovaSpacerad1

Semester 1 Bonding Lecture1
16. 10. 2007
0 views

Semester 1 Bonding Lecture1

Drama Overview
17. 10. 2007
0 views

Drama Overview

04g LINK UNISO MIS SIM 02 2001
24. 10. 2007
0 views

04g LINK UNISO MIS SIM 02 2001

Creativity Perl 3 21 07
16. 10. 2007
0 views

Creativity Perl 3 21 07

Chapter17
11. 12. 2007
0 views

Chapter17

Preparing Proposal
02. 11. 2007
0 views

Preparing Proposal

SC tudor exploration
22. 08. 2007
0 views

SC tudor exploration

aviation fuel
07. 11. 2007
0 views

aviation fuel

Toyota
14. 11. 2007
0 views

Toyota

1 ZoonosesIntro Dunne
19. 11. 2007
0 views

1 ZoonosesIntro Dunne

C130a
20. 11. 2007
0 views

C130a

LingTyp Morphological typology
10. 10. 2007
0 views

LingTyp Morphological typology

entailment WS05
25. 09. 2007
0 views

entailment WS05

radev summtutorial00
22. 08. 2007
0 views

radev summtutorial00

Mary Tudor
22. 08. 2007
0 views

Mary Tudor

acl tutorial
22. 08. 2007
0 views

acl tutorial

Haze Consult 032207
22. 08. 2007
0 views

Haze Consult 032207

abn13
02. 08. 2007
0 views

abn13

crane
02. 08. 2007
0 views

crane

Childhood Obesity
02. 08. 2007
0 views

Childhood Obesity

303lec21
02. 08. 2007
0 views

303lec21

05 conceptual models
25. 09. 2007
0 views

05 conceptual models

CP Morocco
24. 10. 2007
0 views

CP Morocco

Grama
25. 09. 2007
0 views

Grama

cvd
02. 08. 2007
0 views

cvd

NIH talk
16. 10. 2007
0 views

NIH talk

ChestnutBlight
04. 01. 2008
0 views

ChestnutBlight

dbaFile4218
17. 10. 2007
0 views

dbaFile4218

model lite
25. 09. 2007
0 views

model lite

Genre
19. 02. 2008
0 views

Genre

the retreat to corunna
26. 02. 2008
0 views

the retreat to corunna

natural haze levels II report
22. 08. 2007
0 views

natural haze levels II report

Ben Ritchey 1150223453
29. 02. 2008
0 views

Ben Ritchey 1150223453

career capstone 2007
16. 11. 2007
0 views

career capstone 2007

trainingv1 7
25. 03. 2008
0 views

trainingv1 7

18marweb
30. 03. 2008
0 views

18marweb

20080129e1
09. 04. 2008
0 views

20080129e1

Toolkit Hwys cq Moscow Feb2005
10. 04. 2008
0 views

Toolkit Hwys cq Moscow Feb2005

chapter 3
13. 04. 2008
0 views

chapter 3

krugmanobstfeldch08
04. 10. 2007
0 views

krugmanobstfeldch08

venezuela
14. 04. 2008
0 views

venezuela

lovelock01
17. 04. 2008
0 views

lovelock01

Overheads
17. 04. 2008
0 views

Overheads

C 88
02. 08. 2007
0 views

C 88

dds d
19. 06. 2007
0 views

dds d

DC E Show
19. 06. 2007
0 views

DC E Show

dmtshop
19. 06. 2007
0 views

dmtshop

Disciplinary
19. 06. 2007
0 views

Disciplinary

Squazzoni
05. 01. 2008
0 views

Squazzoni

eBook v1
18. 06. 2007
0 views

eBook v1

e 3 MultiCom Product Writeup
18. 06. 2007
0 views

e 3 MultiCom Product Writeup

Dulsa 2007
18. 06. 2007
0 views

Dulsa 2007

GP Reg Slides 07
22. 08. 2007
0 views

GP Reg Slides 07

Mountainbldg
03. 10. 2007
0 views

Mountainbldg

Caregivers
02. 08. 2007
0 views

Caregivers

ZimbZWICAConstruct
30. 12. 2007
0 views

ZimbZWICAConstruct

Placebos Goldstein
26. 10. 2007
0 views

Placebos Goldstein

Bickley
02. 08. 2007
0 views

Bickley

cricket cartoons n cars quiz 4
15. 06. 2007
0 views

cricket cartoons n cars quiz 4

Collaboratory Project Citizen
15. 06. 2007
0 views

Collaboratory Project Citizen

clowns
15. 06. 2007
0 views

clowns

Ch 8 LOVE
15. 06. 2007
0 views

Ch 8 LOVE

Cartoons presentation
15. 06. 2007
0 views

Cartoons presentation

Cartoons 1
15. 06. 2007
0 views

Cartoons 1

The Labors of Hercules
22. 08. 2007
0 views

The Labors of Hercules

tamer sen origin belgrade
26. 11. 2007
0 views

tamer sen origin belgrade

Diaporama Harry P
19. 06. 2007
0 views

Diaporama Harry P

Nyiri
24. 11. 2007
0 views

Nyiri

Elperiodismo
18. 06. 2007
0 views

Elperiodismo

April4 section1
27. 11. 2007
0 views

April4 section1

Dedolfijntjesbij Tom Carine
19. 06. 2007
0 views

Dedolfijntjesbij Tom Carine

detailed
19. 06. 2007
0 views

detailed

DiapoEspagnol
23. 10. 2007
0 views

DiapoEspagnol

enum 4
11. 10. 2007
0 views

enum 4

cookcu talk
15. 06. 2007
0 views

cookcu talk

bping
14. 03. 2008
0 views

bping

28321
24. 02. 2008
0 views

28321

proton6894
22. 10. 2007
0 views

proton6894

Osteosarcoma greyhound
17. 11. 2007
0 views

Osteosarcoma greyhound

akj501
15. 11. 2007
0 views

akj501

ernst
25. 09. 2007
0 views

ernst

107 09 6
22. 08. 2007
0 views

107 09 6