opis sieci neuronowej

background image

=== Run information ===

Scheme:; weka.classifiers.functions.MultilayerPerceptron -L 0.3 -M 0.2 -N 3 -V

0 -S 0 -E 20 -H a -R
Relation:; forestfires_data3.arff

Instances:;517
Attributes: 13

;;; X
;;; Y

;;; 1th
;;; day

;;; FFMC
;;; DMC

;;; DC
;;; ISI

;;; temp
;;; RH

;;; wind
;;; rain

;;; area
Test mode:;split 80.0% train, remainder test

=== Classifier model (full training set) ===

Linear Node 0

Inputs

Weights

Threshold 0.12196549670090634
Node 1

-0.28432395633494856

Node 2

-0.5132765622672993

Node 3

-0.20433555078383572

Node 4

-0.5440289404426354

Node 5

-0.42565204827897773

Node 6

-0.6116203707798075

Sigmoid Node 1

Inputs

Weights

Threshold

-0.9208365171734852

Attrib X

-0.1342313244474802

Attrib Y

0.1424905149866517

Attrib 1th

-0.32495513709450485

Attrib day

0.01635764108915409

Attrib FFMC -0.8114018374628422
Attrib DMC

0.11267577164742565

Attrib DC

-0.36555117626997846

Attrib ISI

0.5862943948859779

Attrib temp -0.1720202748897845
Attrib RH

0.36339336331341077

Attrib wind 0.1830745038084721
Attrib rain 0.8834661111204186

Sigmoid Node 2

Inputs

Weights

background image

Threshold

-0.9046751510543067

Attrib X

-0.325884143692609

Attrib Y

0.11382682786030175

Attrib 1th

-0.4752101439741452

Attrib day

0.05659215077258318

Attrib FFMC -0.8108307370571715
Attrib DMC

0.031215855782300236

Attrib DC

-0.5700503467755056

Attrib ISI

0.46819196847802025

Attrib temp -0.19103412186821614
Attrib RH

0.35404930533510914

Attrib wind 0.14155925793817067
Attrib rain 0.8464946954866757

Sigmoid Node 3

Inputs

Weights

Threshold

-0.949074404390852

Attrib X

-0.06019554619427099

Attrib Y

0.18938997974918145

Attrib 1th

-0.284647450364356

Attrib day

0.05203173896492455

Attrib FFMC -0.801836266163653
Attrib DMC

0.10152091310213567

Attrib DC

-0.3137097529681039

Attrib ISI

0.5368267818615459

Attrib temp -0.12320870357103769
Attrib RH

0.28743155647209634

Attrib wind 0.17498354153826404
Attrib rain 0.9490732153178197

Sigmoid Node 4

Inputs

Weights

Threshold

-0.8589954869955129

Attrib X

-0.3655429181525916

Attrib Y

0.15082245554318813

Attrib 1th

-0.462355616670765

Attrib day

0.03971986547441621

Attrib FFMC -0.8380096547036076
Attrib DMC

0.05566950341671758

Attrib DC

-0.6016646062463429

Attrib ISI

0.5349683490560989

Attrib temp -0.22595451650030476
Attrib RH

0.3976624427339417

Attrib wind 0.10241396478175657

background image

Attrib rain 0.7834876145850634

Sigmoid Node 5

Inputs

Weights

Threshold

-0.9285216973443966

Attrib X

-0.23726620354882555

Attrib Y

0.18599621617391165

Attrib 1th

-0.3788316639109996

Attrib day

0.11312974638189148

Attrib FFMC -0.8488835436700313
Attrib DMC

0.03099165590281007

Attrib DC

-0.43611075637660707

Attrib ISI

0.4903202106489813

Attrib temp -0.17895739532809166
Attrib RH

0.3976533335866728

Attrib wind 0.14739859545640613
Attrib rain 0.8167087677385559

Sigmoid Node 6

Inputs

Weights

Threshold

-0.8969465793673704

Attrib X

-0.44015419954680174

Attrib Y

0.08527269138060303

Attrib 1th

-0.5780999981766523

Attrib day

-0.013757569641490885

Attrib FFMC -0.8533858759181143
Attrib DMC

0.10410182694809936

Attrib DC

-0.6011990892644782

Attrib ISI

0.45784937806745896

Attrib temp -0.24463436370757896
Attrib RH

0.4170057785265738

Attrib wind 0.07649092012237642
Attrib rain 0.7349270084965877

Class
Input

Node 0

Time taken to build model: 0.05 seconds

=== Evaluation on test split ===

=== Summary ===

Correlation coefficient

0.0534

Mean absolute error

0.4959

Root mean squared error

0.5167

Relative absolute error

99.1261 %

Root relative squared error

103.1033 %

Total Number of Instances

103;


Wyszukiwarka

Podobne podstrony:
Matlab opis sieci neuronowych
MSI-program-stacjonarne-15h-2011, logistyka, semestr IV, sieci neuronowe w log (metody sztucznej int
Ontogeniczne sieci neuronowe skrypt(1)
04 Wyklad4 predykcja sieci neuronoweid 523 (2)
Pytania egz AGiSN, SiMR - st. mgr, Alg. i Sieci Neuronowe
MSI-ściaga, SiMR - st. mgr, Alg. i Sieci Neuronowe
32 Sieci neuronowe
Identyfikacja Procesów Technologicznych, Identyfikacja charakterystyki statycznej obiektu dynamiczne
sieci neuronowe, Sieci NeuronoweKolos
sztuczne sieci neuronowe sciaga
Identyfikacja Procesów Technologicznych, Identyfikacja charakterystyk statycznych obiektu dynamiczne
Projekt I Sztuczna Inteligencja, Sprawozdanie, Techniczne zastosowanie sieci neuronowych
badania operacyjne, badania operacyjne - skrypt z PUTINF, Sieci neuronowe

więcej podobnych podstron