{"id":875,"date":"2017-01-28T21:56:35","date_gmt":"2017-01-28T21:56:35","guid":{"rendered":"http:\/\/intelligentonlinetools.com\/blog\/?p=875"},"modified":"2017-02-05T22:50:07","modified_gmt":"2017-02-05T22:50:07","slug":"iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters","status":"publish","type":"post","link":"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/","title":{"rendered":"Iris Plant Classification Using Neural Network – Online Experiments with Normalization and Other Parameters"},"content":{"rendered":"

Do we need to normalize input data for neural network? How differently will be results from running normalized and non normalized data? This will be explored in the post using Online Machine Learning Algorithms<\/a> tool for classification of iris data set with feed-forward neural network. <\/p>\n

Feed-forward Neural Network<\/strong>
\nFeed-forward neural networks are commonly used for classification. In this example we choose feed-forward neural network with back propagation training and gradient descent optimization method. <\/p>\n

Our neural network has one hidden layer. The number of neuron units in this hidden layer and learning rate can be set by user. We do not need to code neural network because we use online tool that is taking training, testing data, number of neurons in hidden layer and learning rate parameters as input. <\/p>\n

The output from this tool is classification results for testing data set, neural network weights and deltas at different iterations.<\/p>\n

Data Set<\/strong>
\nAs mentioned above we use iris data set for data input to neural network. The data set contains 3 classes of 50 instances each, where each class refers to a type of iris plant. [1] We remove first 3 rows for each class and save for testing data set. Thus the input data set has 141 rows and testing data set has 9 rows. <\/p>\n

Normalization<\/strong>
\nWe run neural network first time without normalization of input data. Then we run neural network with normalized data.
\nWe use min max normalization which can be described by formula [2]:
\n xij = (xij – colmmin) \/(colmmax – colmmin)<\/strong><\/p>\n

Where
\n colmmin = minimum value of the column
\n colmmax = maximum value of the column
\n xij = x(data item) present at ithrow and jthcolumn<\/p>\n

Normalization is applied to both X and Y, so the possible values for Y become 0, 05, 1
\nand X become like :
\n0.083333333\t0.458333333\t0.084745763\t0.041666667<\/p>\n

You can view normalized data at this link : Iris Data Set – Normalized Data<\/a><\/p>\n

Online Tool<\/strong>
\nOnce data is ready we can to load data to neural network and run classification. Here are the steps how to use online Machine Learning Algorithms tool:
\n1.Access the link Online Machine Learning Algorithms<\/a> with feed-forward neural network.
\n2.Select algorithm and click Load parameters for this model<\/em>.
\n3.Input the data that you want to run.
\n4.Click Run now<\/em>.
\n5.Click results<\/em> link
\n6.Click Refresh<\/em> button on this new page, you maybe will need click few times untill you see data output.
\n7.Scroll to the bottom page to see calculations.
\nFor more detailed instruction use this link: How to Run Online Machine Learning Algorithms Tool<\/a><\/p>\n

Experiments<\/strong>
\nWe do 4 experiments as shown in the table below: 1 without normalization, and 3 with normalization and various learning rate and number of neurons hidden. Results are shown in the same table and the error graph shown below under the table. When iris data set was inputted without normalization, the text label is changed to numerical variable with values -1,0,1 The result is not satisfying with needed accuracy level. So decision is made to normalize data using min max method.<\/p>\n

Here is the sample result from the last experiment, with the lowest error. The learning rate is 0.1 and the number of hidden neurons is 36. The delta error in the end of training is 1.09.<\/p>\n

[[ 0.00416852]
\n[ 0.01650389]
\n[ 0.01021347]
\n[ 0.43996485]
\n[ 0.50235484]
\n[ 0.58338683]
\n[ 0.80222148]
\n[ 0.92640374]
\n[ 0.93291573]] <\/p>\n

Results<\/strong><\/p>\n\n\n\n\n\n\n
\nNorma
lization\n<\/td>\n		Learn. Rate<\/td>\nHidden units #<\/td>\n\nCorrect\n<\/td>\n\nTotal\n<\/td>\n\nAccuracy\n<\/td>\n\nDelta Error\n<\/td>\n<\/tr>\n
\nNo<\/p>\n<\/td>\n0.5<\/td>\n4<\/td>\n\n3\n<\/td>\n\n9\n<\/td>\n\n33%\n<\/td>\n\n9.7\n<\/td>\n<\/tr>\n
\nYes (Min Max)<\/p>\n<\/td>\n0.5<\/td>\n4<\/td>\n\n8\n<\/td>\n\n9\n<\/td>\n\n89%\n<\/td>\n\n1.25\n<\/td>\n<\/tr>\n
\nYes (Min Max)<\/p>\n<\/td>\n0.1<\/td>\n4<\/td>\n\n9\n<\/td>\n\n9\n<\/td>\n\n100%\n<\/td>\n\n1.19\n<\/td>\n<\/tr>\n
\nYes (Min Max)<\/p>\n<\/td>\n0.1<\/td>\n36<\/td>\n\n9\n<\/td>\n\n9\n<\/td>\n\n100%\n<\/td>\n\n1.09\n<\/td>\n<\/tr>\n<\/table>\n

\"\"<\/p>\n

Conclusion<\/strong>
\nNormalization can make huge difference on results. Further improvements are posible by adjusting learning rate or number hidden units in the hidden layer. <\/p>\n

References<\/strong><\/p>\n

1. Iris Data Set <\/a>
\n2. AN APPROACH FOR IRIS PLANT CLASSIFICATION USING NEURAL NETWORK<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Do we need to normalize input data for neural network? How differently will be results from running normalized and non normalized data? This will be explored in the post using Online Machine Learning Algorithms tool for classification of iris data set with feed-forward neural network. Feed-forward Neural Network Feed-forward neural networks are commonly used for … Read more<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"jetpack_publicize_message":"","jetpack_is_tweetstorm":false,"jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":[]},"categories":[5,2,9,10],"tags":[],"jetpack_publicize_connections":[],"yoast_head":"\nIris Plant Classification Using Neural Network - Online Experiments with Normalization and Other Parameters - Machine Learning Applications<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Iris Plant Classification Using Neural Network - Online Experiments with Normalization and Other Parameters - Machine Learning Applications\" \/>\n<meta property=\"og:description\" content=\"Do we need to normalize input data for neural network? How differently will be results from running normalized and non normalized data? This will be explored in the post using Online Machine Learning Algorithms tool for classification of iris data set with feed-forward neural network. Feed-forward Neural Network Feed-forward neural networks are commonly used for ... Read more\" \/>\n<meta property=\"og:url\" content=\"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/\" \/>\n<meta property=\"og:site_name\" content=\"Machine Learning Applications\" \/>\n<meta property=\"article:published_time\" content=\"2017-01-28T21:56:35+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2017-02-05T22:50:07+00:00\" \/>\n<meta property=\"og:image\" content=\"http:\/\/intelligentonlinetools.com\/blog\/wp-content\/uploads\/2017\/01\/delta-error-graph-from-iris-data-set-36-neurons-300x231.png\" \/>\n<meta name=\"author\" content=\"owygs156\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"owygs156\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/\",\"url\":\"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/\",\"name\":\"Iris Plant Classification Using Neural Network - Online Experiments with Normalization and Other Parameters - Machine Learning Applications\",\"isPartOf\":{\"@id\":\"http:\/\/intelligentonlinetools.com\/blog\/#website\"},\"datePublished\":\"2017-01-28T21:56:35+00:00\",\"dateModified\":\"2017-02-05T22:50:07+00:00\",\"author\":{\"@id\":\"http:\/\/intelligentonlinetools.com\/blog\/#\/schema\/person\/7a886dc5eb9758369af2f6d2cb342478\"},\"breadcrumb\":{\"@id\":\"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"http:\/\/intelligentonlinetools.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Iris Plant Classification Using Neural Network – Online Experiments with Normalization and Other Parameters\"}]},{\"@type\":\"WebSite\",\"@id\":\"http:\/\/intelligentonlinetools.com\/blog\/#website\",\"url\":\"http:\/\/intelligentonlinetools.com\/blog\/\",\"name\":\"Machine Learning Applications\",\"description\":\"Artificial intelligence, data mining and machine learning for building web based tools and services.\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"http:\/\/intelligentonlinetools.com\/blog\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"http:\/\/intelligentonlinetools.com\/blog\/#\/schema\/person\/7a886dc5eb9758369af2f6d2cb342478\",\"name\":\"owygs156\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"http:\/\/intelligentonlinetools.com\/blog\/#\/schema\/person\/image\/\",\"url\":\"http:\/\/2.gravatar.com\/avatar\/b351def598609cb4c0b5bca26497c7e5?s=96&d=mm&r=g\",\"contentUrl\":\"http:\/\/2.gravatar.com\/avatar\/b351def598609cb4c0b5bca26497c7e5?s=96&d=mm&r=g\",\"caption\":\"owygs156\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Iris Plant Classification Using Neural Network - Online Experiments with Normalization and Other Parameters - Machine Learning Applications","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/","og_locale":"en_US","og_type":"article","og_title":"Iris Plant Classification Using Neural Network - Online Experiments with Normalization and Other Parameters - Machine Learning Applications","og_description":"Do we need to normalize input data for neural network? How differently will be results from running normalized and non normalized data? This will be explored in the post using Online Machine Learning Algorithms tool for classification of iris data set with feed-forward neural network. Feed-forward Neural Network Feed-forward neural networks are commonly used for ... Read more","og_url":"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/","og_site_name":"Machine Learning Applications","article_published_time":"2017-01-28T21:56:35+00:00","article_modified_time":"2017-02-05T22:50:07+00:00","og_image":[{"url":"http:\/\/intelligentonlinetools.com\/blog\/wp-content\/uploads\/2017\/01\/delta-error-graph-from-iris-data-set-36-neurons-300x231.png"}],"author":"owygs156","twitter_card":"summary_large_image","twitter_misc":{"Written by":"owygs156","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/","url":"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/","name":"Iris Plant Classification Using Neural Network - Online Experiments with Normalization and Other Parameters - Machine Learning Applications","isPartOf":{"@id":"http:\/\/intelligentonlinetools.com\/blog\/#website"},"datePublished":"2017-01-28T21:56:35+00:00","dateModified":"2017-02-05T22:50:07+00:00","author":{"@id":"http:\/\/intelligentonlinetools.com\/blog\/#\/schema\/person\/7a886dc5eb9758369af2f6d2cb342478"},"breadcrumb":{"@id":"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/"]}]},{"@type":"BreadcrumbList","@id":"http:\/\/intelligentonlinetools.com\/blog\/2017\/01\/28\/iris-plant-classification-using-neural-network-online-experiments-with-normalization-and-other-parameters\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"http:\/\/intelligentonlinetools.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Iris Plant Classification Using Neural Network – Online Experiments with Normalization and Other Parameters"}]},{"@type":"WebSite","@id":"http:\/\/intelligentonlinetools.com\/blog\/#website","url":"http:\/\/intelligentonlinetools.com\/blog\/","name":"Machine Learning Applications","description":"Artificial intelligence, data mining and machine learning for building web based tools and services.","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"http:\/\/intelligentonlinetools.com\/blog\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"http:\/\/intelligentonlinetools.com\/blog\/#\/schema\/person\/7a886dc5eb9758369af2f6d2cb342478","name":"owygs156","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"http:\/\/intelligentonlinetools.com\/blog\/#\/schema\/person\/image\/","url":"http:\/\/2.gravatar.com\/avatar\/b351def598609cb4c0b5bca26497c7e5?s=96&d=mm&r=g","contentUrl":"http:\/\/2.gravatar.com\/avatar\/b351def598609cb4c0b5bca26497c7e5?s=96&d=mm&r=g","caption":"owygs156"}}]}},"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p7h1IJ-e7","jetpack-related-posts":[{"id":1178,"url":"http:\/\/intelligentonlinetools.com\/blog\/2017\/05\/14\/time-series-prediction-with-convolutional-neural-networks\/","url_meta":{"origin":875,"position":0},"title":"Forecasting Time Series Data with Convolutional Neural Networks","date":"May 14, 2017","format":false,"excerpt":"Convolutional neural networks(CNN) is increasingly important concept in computer science and finds more and more applications in different fields. Many posts on the web are about applying convolutional neural networks for image classification as CNN is very useful type of neural networks for image classification. But convolutional neural networks can\u2026","rel":"","context":"In "Artificial Intelligence"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/intelligentonlinetools.com\/blog\/wp-content\/uploads\/2017\/05\/time-series-LSTM-300x164.png?resize=350%2C200","width":350,"height":200},"classes":[]},{"id":621,"url":"http:\/\/intelligentonlinetools.com\/blog\/2016\/10\/09\/online-resources-for-neural-networks-with-python\/","url_meta":{"origin":875,"position":1},"title":"Online Resources for Neural Networks with Python","date":"October 9, 2016","format":false,"excerpt":"The neural network field enjoys now a resurgence of interest. New training techniques made training deep networks feasible. With deeper networks, more training data and powerful new hardware to make it all work, deep neural networks (or \u201cdeep learning\u201d systems) suddenly began making rapid progress in areas such as speech\u2026","rel":"","context":"In "Artificial Intelligence"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":2194,"url":"http:\/\/intelligentonlinetools.com\/blog\/2018\/08\/11\/applied-machine-learning-classification-for-decision-making\/","url_meta":{"origin":875,"position":2},"title":"Applied Machine Learning Classification for Decision Making","date":"August 11, 2018","format":false,"excerpt":"Making the good decision is the challenge that we often have. So, in this post, we will look at how applied machine learning classification can be used for the process of decision making. The simple and quick approach to make decision is follow our past experience of similar situations. Usually\u2026","rel":"","context":"In "Artificial Intelligence"","img":{"alt_text":"Decision Making","src":"https:\/\/i0.wp.com\/intelligentonlinetools.com\/blog\/wp-content\/uploads\/2018\/08\/signs-1172211_640-e1534384498570.jpg?resize=350%2C200","width":350,"height":200},"classes":[]},{"id":2259,"url":"http:\/\/intelligentonlinetools.com\/blog\/2018\/09\/06\/artificial-intelligence-neural-networks-applications-seismic-prospecting\/","url_meta":{"origin":875,"position":3},"title":"Artificial Intelligence – Neural Networks Applications in Seismic Prospecting","date":"September 6, 2018","format":false,"excerpt":"TUSHAR website Introduction Large volumes of hydrocarbons remain to be found in the world. Finding and extracting these hydrocarbons is difficult and expensive. We believe that under-utilization of data, and of the existing subsurface knowledge base, are at least partly responsible for the disappointing exploration performance. Furthermore, we argue that\u2026","rel":"","context":"In "Neural Networks Applications"","img":{"alt_text":"Global map","src":"https:\/\/i0.wp.com\/intelligentonlinetools.com\/blog\/wp-content\/uploads\/2018\/09\/global_map-e1536320690373.png?resize=350%2C200","width":350,"height":200},"classes":[]},{"id":9,"url":"http:\/\/intelligentonlinetools.com\/blog\/2016\/01\/30\/general-regression-neural-networks\/","url_meta":{"origin":875,"position":4},"title":"General Regression Neural Networks","date":"January 30, 2016","format":false,"excerpt":"General Regression Neural Networks (GRNN) is one of the type of neural networks with a one pass learning algorithm. The simplicity of algorithm for GRNN is one of the advantage of this neural network and many researchers use it. In one of recent paper was proposed algorithm that is using\u2026","rel":"","context":"Similar post","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":1783,"url":"http:\/\/intelligentonlinetools.com\/blog\/2018\/01\/19\/machine-learning-stock-prediction-lstm-keras\/","url_meta":{"origin":875,"position":5},"title":"Machine Learning Stock Prediction with LSTM and Keras","date":"January 19, 2018","format":false,"excerpt":"In this post I will share experiments on machine learning stock prediction with LSTM and Keras with one step ahead. I tried to do first multiple steps ahead with few techniques described in the papers on the web. But I discovered that I need fully understand and test the simplest\u2026","rel":"","context":"In "Machine Learning"","img":{"alt_text":"Forecasting one step ahead LSTM 60","src":"https:\/\/i0.wp.com\/intelligentonlinetools.com\/blog\/wp-content\/uploads\/2018\/01\/Forecasting-one-step-ahead-LSTM-60-3_1_2018.png?resize=350%2C200","width":350,"height":200},"classes":[]}],"_links":{"self":[{"href":"http:\/\/intelligentonlinetools.com\/blog\/wp-json\/wp\/v2\/posts\/875"}],"collection":[{"href":"http:\/\/intelligentonlinetools.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/intelligentonlinetools.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/intelligentonlinetools.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/intelligentonlinetools.com\/blog\/wp-json\/wp\/v2\/comments?post=875"}],"version-history":[{"count":32,"href":"http:\/\/intelligentonlinetools.com\/blog\/wp-json\/wp\/v2\/posts\/875\/revisions"}],"predecessor-version":[{"id":963,"href":"http:\/\/intelligentonlinetools.com\/blog\/wp-json\/wp\/v2\/posts\/875\/revisions\/963"}],"wp:attachment":[{"href":"http:\/\/intelligentonlinetools.com\/blog\/wp-json\/wp\/v2\/media?parent=875"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/intelligentonlinetools.com\/blog\/wp-json\/wp\/v2\/categories?post=875"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/intelligentonlinetools.com\/blog\/wp-json\/wp\/v2\/tags?post=875"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}