ROOT PAT ROOT TES ROOT WGT ROOT FWT
![ROOT. PAT ROOT. TES (ROOT. WGT) (ROOT. FWT) (ROOT. DBD) • Use Analyze root ROOT. PAT ROOT. TES (ROOT. WGT) (ROOT. FWT) (ROOT. DBD) • Use Analyze root](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-1.jpg)
![• ANALYZE = Meta. Neural Alternative Code • Either run meta root analyze • ANALYZE = Meta. Neural Alternative Code • Either run meta root analyze](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-2.jpg)
![Meta. Neural Input File for the ROOT 4 => 4 layers 2 => 2 Meta. Neural Input File for the ROOT 4 => 4 layers 2 => 2](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-3.jpg)
![EXAMPLE DATA SETS • IRIS data • Checkerboard data • Svante wold’s QSAR data EXAMPLE DATA SETS • IRIS data • Checkerboard data • Svante wold’s QSAR data](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-4.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-5.jpg)
![FILES RELATED TO CHECKERBOARD EXAMPLE CHECK_DATA. BAT CHECK_NET. BAT CHECK_TEST. BAT CHECK. PAT FILES RELATED TO CHECKERBOARD EXAMPLE CHECK_DATA. BAT CHECK_NET. BAT CHECK_TEST. BAT CHECK. PAT](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-6.jpg)
![Meta. Neural INPUT FILE FOR CHECKERBOARD DATA Meta. Neural INPUT FILE FOR CHECKERBOARD DATA](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-7.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-8.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-9.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-10.jpg)
![QSAR DATA SET EXAMPLE: 19 Amino Acids From Svante Wold, Michael Sjölström, Lennart Erikson, QSAR DATA SET EXAMPLE: 19 Amino Acids From Svante Wold, Michael Sjölström, Lennart Erikson,](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-11.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-12.jpg)
![PLS 1 latent variable PLS 1 latent variable](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-13.jpg)
![PLS 1 latent variable No aromatic AAs PLS 1 latent variable No aromatic AAs](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-14.jpg)
![1 latent variable Gaussian Kernel PLS (sigma = 1. 3) With aromatic AAs 1 latent variable Gaussian Kernel PLS (sigma = 1. 3) With aromatic AAs](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-15.jpg)
![Chemoinformatic Models to Predict Binding Affinities to Human Serum Albumin: G. Colmenarejo et. al. Chemoinformatic Models to Predict Binding Affinities to Human Serum Albumin: G. Colmenarejo et. al.](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-16.jpg)
![• Binding affinities to human serum albumin (HSA): log K’hsa • Gonzalo Colmenarejo, • Binding affinities to human serum albumin (HSA): log K’hsa • Gonzalo Colmenarejo,](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-17.jpg)
![Electron Density-Derived TAE-wavelet Descriptors 1 ) Surface properties are encoded on 0. 002 e/au Electron Density-Derived TAE-wavelet Descriptors 1 ) Surface properties are encoded on 0. 002 e/au](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-18.jpg)
![PEST-Shape Descriptors: Surface Property-Encoded Ray Tracing • TAE Internal Ray Reflection - low resolution PEST-Shape Descriptors: Surface Property-Encoded Ray Tracing • TAE Internal Ray Reflection - low resolution](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-19.jpg)
![Shape-Aware Molecular Descriptors from Property/Segment-Length Distributions • Segment length and point-of-incidence value form 2 Shape-Aware Molecular Descriptors from Property/Segment-Length Distributions • Segment length and point-of-incidence value form 2](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-20.jpg)
![training training](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-21.jpg)
![testing testing](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-22.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-23.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-24.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-25.jpg)
![CHERKASSKY’S NONLINEAR BENCHMARK DATA • Generate 500 datapoints (400 training; 100 testing) for: Cherkas. CHERKASSKY’S NONLINEAR BENCHMARK DATA • Generate 500 datapoints (400 training; 100 testing) for: Cherkas.](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-26.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-27.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-28.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-29.jpg)
![Y=sin|x|/|x| • Generate 500 datapoints (100 training; 500 testing) for: Y=sin|x|/|x| • Generate 500 datapoints (100 training; 500 testing) for:](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-30.jpg)
![Comparison Kernel-PLS with PLS 4 latent variables sigma = 0. 08 PLS Kernel-PLS Comparison Kernel-PLS with PLS 4 latent variables sigma = 0. 08 PLS Kernel-PLS](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-31.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-32.jpg)
- Slides: 32
![ROOT PAT ROOT TES ROOT WGT ROOT FWT ROOT DBD Use Analyze root ROOT. PAT ROOT. TES (ROOT. WGT) (ROOT. FWT) (ROOT. DBD) • Use Analyze root](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-1.jpg)
ROOT. PAT ROOT. TES (ROOT. WGT) (ROOT. FWT) (ROOT. DBD) • Use Analyze root – 34 for easy way (the file meta let you override defaults) • Use meta root for full mode - e. g meta root - use Meta. UI for input file Meta. Neural ROOT. XXX ROOT. TTT ROOT. TRN (ROOT. DBD) ROOT. WGT ROOT. FWT
![ANALYZE Meta Neural Alternative Code Either run meta root analyze • ANALYZE = Meta. Neural Alternative Code • Either run meta root analyze](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-2.jpg)
• ANALYZE = Meta. Neural Alternative Code • Either run meta root analyze root. pat – 34 (single training and testing) analyze root. pat – 3434 (LOO) analyze root. txt 34 (bootstrap mode) • Results for analyze are in resultss. xxx and resultss. ttt • Results from Meta. Neural are in root. xxx and root. ttt • Meta. Neural input file is generated automatically in analyze • The file name meta overrides the default input file for analyze S S S
![Meta Neural Input File for the ROOT 4 4 layers 2 2 Meta. Neural Input File for the ROOT 4 => 4 layers 2 => 2](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-3.jpg)
Meta. Neural Input File for the ROOT 4 => 4 layers 2 => 2 inputs 16 => # hidden neurons in layer #1 4 => # hidden neurons in layer# 2 1 => # outputs 300 => epoch length (hint: always use 1, for the entire batch) 0. 01 => learning parameters by weight layer (hint: 1/# patterns or 1/# epochs) 0. 01 0. 5 => momentum parameters by weight layer (hint use 0. 5) 0. 5 10000000 => some very large number of training epochs 200 => error display refresh rate 1 =>sigmoid transfer function 1 => Temperature of sigmoid check. pat => name of file with training patterns (test patterns in root. tes) 0 => not used (legacy entry) 100 => not used (legacy entry) 0. 02000 => exit training if error < 0. 02 0 => initial weights from a flat random distribution 0. 2 => initial random weights all fall between – 2 and +2
![EXAMPLE DATA SETS IRIS data Checkerboard data Svante wolds QSAR data EXAMPLE DATA SETS • IRIS data • Checkerboard data • Svante wold’s QSAR data](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-4.jpg)
EXAMPLE DATA SETS • IRIS data • Checkerboard data • Svante wold’s QSAR data • Cherkassky’s nonlinear function • Albumin QSAR data
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-5.jpg)
![FILES RELATED TO CHECKERBOARD EXAMPLE CHECKDATA BAT CHECKNET BAT CHECKTEST BAT CHECK PAT FILES RELATED TO CHECKERBOARD EXAMPLE CHECK_DATA. BAT CHECK_NET. BAT CHECK_TEST. BAT CHECK. PAT](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-6.jpg)
FILES RELATED TO CHECKERBOARD EXAMPLE CHECK_DATA. BAT CHECK_NET. BAT CHECK_TEST. BAT CHECK. PAT
![Meta Neural INPUT FILE FOR CHECKERBOARD DATA Meta. Neural INPUT FILE FOR CHECKERBOARD DATA](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-7.jpg)
Meta. Neural INPUT FILE FOR CHECKERBOARD DATA
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-8.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-9.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-10.jpg)
![QSAR DATA SET EXAMPLE 19 Amino Acids From Svante Wold Michael Sjölström Lennart Erikson QSAR DATA SET EXAMPLE: 19 Amino Acids From Svante Wold, Michael Sjölström, Lennart Erikson,](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-11.jpg)
QSAR DATA SET EXAMPLE: 19 Amino Acids From Svante Wold, Michael Sjölström, Lennart Erikson, "PLS-regression: a basic tool of chemometrics, " Chemometrics and Intelligent Laboratory Systems, Vol 58, pp. 109 -130 (2001) RENSSELAER
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-12.jpg)
![PLS 1 latent variable PLS 1 latent variable](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-13.jpg)
PLS 1 latent variable
![PLS 1 latent variable No aromatic AAs PLS 1 latent variable No aromatic AAs](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-14.jpg)
PLS 1 latent variable No aromatic AAs
![1 latent variable Gaussian Kernel PLS sigma 1 3 With aromatic AAs 1 latent variable Gaussian Kernel PLS (sigma = 1. 3) With aromatic AAs](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-15.jpg)
1 latent variable Gaussian Kernel PLS (sigma = 1. 3) With aromatic AAs
![Chemoinformatic Models to Predict Binding Affinities to Human Serum Albumin G Colmenarejo et al Chemoinformatic Models to Predict Binding Affinities to Human Serum Albumin: G. Colmenarejo et. al.](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-16.jpg)
Chemoinformatic Models to Predict Binding Affinities to Human Serum Albumin: G. Colmenarejo et. al. , J. Med. Chem 2001, 44, pp. 4370 -4378
![Binding affinities to human serum albumin HSA log Khsa Gonzalo Colmenarejo • Binding affinities to human serum albumin (HSA): log K’hsa • Gonzalo Colmenarejo,](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-17.jpg)
• Binding affinities to human serum albumin (HSA): log K’hsa • Gonzalo Colmenarejo, Galaxo. Smith. Kline J. Med. Chem. 2001, 44, 4370 -4378 • 95 molecules, 250 -1500+ descriptors • Widely different compounts
![Electron DensityDerived TAEwavelet Descriptors 1 Surface properties are encoded on 0 002 eau Electron Density-Derived TAE-wavelet Descriptors 1 ) Surface properties are encoded on 0. 002 e/au](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-18.jpg)
Electron Density-Derived TAE-wavelet Descriptors 1 ) Surface properties are encoded on 0. 002 e/au 3 surface Breneman, C. M. and Rhem, M. , J. Comp. Chem. , 1997, 18(2), p. 182 -197 2 ) Histograms or wavelet encoded of surface properties give TAE property descriptors Histograms PIP (Local Ionization Potential) Wavelet Coefficients
![PESTShape Descriptors Surface PropertyEncoded Ray Tracing TAE Internal Ray Reflection low resolution PEST-Shape Descriptors: Surface Property-Encoded Ray Tracing • TAE Internal Ray Reflection - low resolution](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-19.jpg)
PEST-Shape Descriptors: Surface Property-Encoded Ray Tracing • TAE Internal Ray Reflection - low resolution scan Isosurface (portion removed) with 750 segments RENSSELAER
![ShapeAware Molecular Descriptors from PropertySegmentLength Distributions Segment length and pointofincidence value form 2 Shape-Aware Molecular Descriptors from Property/Segment-Length Distributions • Segment length and point-of-incidence value form 2](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-20.jpg)
Shape-Aware Molecular Descriptors from Property/Segment-Length Distributions • Segment length and point-of-incidence value form 2 D-histogram • Each bin of 2 D-histogram becomes a hybrid descriptor – 36 descriptors per hybrid length-property PIP vs Segment Length RENSSELAER
![training training](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-21.jpg)
training
![testing testing](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-22.jpg)
testing
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-23.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-24.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-25.jpg)
![CHERKASSKYS NONLINEAR BENCHMARK DATA Generate 500 datapoints 400 training 100 testing for Cherkas CHERKASSKY’S NONLINEAR BENCHMARK DATA • Generate 500 datapoints (400 training; 100 testing) for: Cherkas.](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-26.jpg)
CHERKASSKY’S NONLINEAR BENCHMARK DATA • Generate 500 datapoints (400 training; 100 testing) for: Cherkas. bat
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-27.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-28.jpg)
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-29.jpg)
![Ysinxx Generate 500 datapoints 100 training 500 testing for Y=sin|x|/|x| • Generate 500 datapoints (100 training; 500 testing) for:](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-30.jpg)
Y=sin|x|/|x| • Generate 500 datapoints (100 training; 500 testing) for:
![Comparison KernelPLS with PLS 4 latent variables sigma 0 08 PLS KernelPLS Comparison Kernel-PLS with PLS 4 latent variables sigma = 0. 08 PLS Kernel-PLS](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-31.jpg)
Comparison Kernel-PLS with PLS 4 latent variables sigma = 0. 08 PLS Kernel-PLS
![](https://slidetodoc.com/presentation_image_h2/02842e3a74121abf98e0daba24281ec1/image-32.jpg)
Root of discipline
Pat pat seguimiento
Tes pat
Perbedaan tes tat dan rorschach
Tes buatan guru dan tes standar
Etika test
Konstruksi soal adalah
Words with the greek root cycl
Amo root words
Capit prefix meaning
Pat 2016
Thomasova dlaha
Pat noventa padovana
Pat winlink
Pat
Pat coso
Good respiration rate
Avoid the obvious content
Pat has atnie
Pat 1
Pallor cyanosis
Pat oglesby
Locadtr
Pat mueller
Pat helland
Graad 11 igo pat taak
Write one word for each space
Pat theory
Pat hintze
Hspice pat
Pat tree example
Same song pat mora analysis
Pat brereton