.. image:: /_images/icons/app_workflows.png :width: 5% :align: right :target: index.html .. |VideoAnalyzer| image:: /_images/icons/icon_MLworkers.png :width: 4% :target: Mlworkers.html .. _mlworkers: ############################### ML Workers ############################### ML Workers or Machine Learning Workers are available in the Workflows to compute data and obtain results. Below are few example of the ML workers. .. _classifierssearch: ********************* Classifiers ********************* All Classifiers workers are now limited to select just one target selection in Workflows. .. video:: _static/movies/classifierssearch.mp4 :width: 100% | .. _searchclass: ********************* Classifiers Search ********************* ML workers can now be searched for classification workers in Workflows .. video:: _static/movies/classifierssearch2.mp4 :width: 100% | .. _learnauto: ********************* ML_LEARN_AUTO ********************* ML_LEARN_AUTO now has all the necessary responses as any other regression method but with the prefix for the best method. .. video:: _static/movies/mllearnauto1.mp4 :width: 100% | .. _rfc: ********************* ML_LEARN_RFC ********************* Added ML_LEARN_RFC worker in Workflows .. video:: _static/movies/mlrfc.mp4 :width: 100% | Added 'Probabilities' output response to RFC worker in Workflows. .. thumbnail:: /_images/Images/probabilitiesrfc.png :title: Probabilities .. centered:: :sup:`Probabilities` | | ************************************* ML_LEARN_SVC ************************************* Added ML_LEARN_SVC worker in Workflows .. video:: _static/movies/mlsvc.mp4 :width: 100% | .. _pca: ************************************* ML_EXPLORE_RUN_PCA ************************************* Added ML_EXPLORE_RUN_PCA worker in Workflows .. thumbnail:: /_images/Images/runpca.png :title: RUN_PCA .. centered:: :sup:`RUN_PCA` | .. _mloutput: ************************************* ML Worker's Output ************************************* We can now assign ML Worker’s output dataset as input to the Report Worker and view the output in Simlytiks after executing the workers. .. video:: _static/movies/mlworkersoutput.mp4 :width: 100% | ML Charts' Output tab Responses now shows a settings bar where the table settings can be changed. .. thumbnail:: /_images/Images/tabresponses.png :title: Table settings .. centered:: :sup:`Table settings` | .. _mlautoclean: ************************************* ML_CLEAN_AUTOCLEAN ************************************* ML_CLEAN_AUTOCLEAN Worker is now available to clean datasets for machine learning applications in Workflows. .. video:: _static/movies/mlautoclean.mp4 :width: 100% | .. _mlpredictinfo: ************************************* ML_PREDICT_INFO ************************************* ML_PREDICT_INFO worker is now available to provide information about the ML workers in Workflows. .. video:: _static/movies/mlpredictinfo.mp4 :width: 100% | ML_PREDICT worker now includes predicted curves compiled from individual points. .. video:: _static/movies/mlpredictedcurves.mp4 :width: 100% | .. _mlpredictinteractive: ************************************* ML_PREDICT_INTERACTIVE ************************************* ML_PREDICT_INTERACTIVE worker is added for interactive predict capability of worker in Workflows. .. video:: _static/movies/mlpredictinteractive.mp4 :width: 100% | ML_PREDICT_INTERACTIVE worker now has two new inputs at the bottom of the list called Original Dataset and Raw column name which will help generate a new CURVE output in this worker after its execution and shows a predicted curve .. video:: _static/movies/mlpredictinteractivenew.mp4 :width: 100% | Two new inputs called Learn Dataset and Curve column name are added for ML_PREDICT worker to reconstruct the curve. .. video:: _static/movies/mlpredictinteractivenew1.mp4 :width: 100% | .. _slidersinteractive: In ML Predict Interactive worker, the Slider input values are added to the prediction dataset in 2 ways. Either by choosing a slider input value and clicking on "add" or by choosing a slider input and just executing the worker. In the second case input values are automatically added.​ .. video:: _static/movies/mlpredictinteractsliders.mp4 :width: 100% | The Dataset inputs in the workers will now allow to remove the row even if the dataset had a single row of columns in Workflows. .. video:: _static/movies/datasetremove.mp4 :width: 100% | A new text input field is added to ML_PREDICT_INTERACTIVE worker next to slider inputs where the values can be added manually and saved to the dataset in Workflows.​ .. thumbnail:: /_images/Images/mltextinput.png :title: Text Input .. centered:: :sup:`Text Input` | | .. _rungridserach: ************************************* RUN GRID SEARCH ************************************* ML Workers have Input option called Run Grid Search. We can see the difference in the Predicted scores after execution of worker with and without Run Grid Search option.​ .. thumbnail:: /_images/Images/rungridserach.png :title: RUN GRID SEARCH .. centered:: :sup:`RUN GRID SEARCH` | .. _300targets: ************************************* 300 Targets ************************************* ML workers with data greater than 300 Targets work as expected. .. video:: _static/movies/300targets.mp4 :width: 100% | .. _crossvalidation: ************************************* Cross Validation ************************************* ML Regression and Classifiers now have a new option called Cross validation in Workflows. Different types of Cross validations are available and they help is validate the responses in the Output .. thumbnail:: /_images/Images/crossvalidation.png :title: Cross Validation .. centered:: :sup:`Cross Validation` | .. _stdout: ************************************* STDOUT Output ************************************* All ML Learn workers now have STDOUT as an output that can be reviewed if there are some issues in workflows .. video:: _static/movies/stdout.mp4 :width: 100% | .. _runpca: ************************************* RUN PCA ************************************* New ML worker called RUN_PCA is added to Workflows which provides 'Variance Ratio' output for components. .. video:: _static/movies/runpca.mp4 :width: 100% | *ML_RUN_PCA worker now has the same normalize options as the *ML_LEARN_LINEAR worker in Workflows. .. video:: _static/movies/runpcanorm.mp4 :width: 100% | .. _mlpregression: ************************************* MLP Regression ************************************* Added more input options to MLP Regression worker in Workflows. .. video:: _static/movies/mlpregression.mp4 :width: 100% | .. _mllinearnorm: ML Linear Regression worker has new scaler options under Normalize input option which helps us to get the overall score for the worker in Workflows. .. video:: _static/movies/mllinearregressionnorm.mp4 :width: 100% | .. _gradientregression: ************************************* Gradient boost regressor ************************************* New worker called *Gradient boost regressor is added to Workflows. .. video:: _static/movies/gradientregress.mp4 :width: 100% | .. _mlworkers: ALL ML Learn workers support curve inputs and targets. .. video:: _static/movies/mllearncurve.mp4 :width: 100% | All ML Learn workers can now take any curve column as either INPUT or TARGET and use digitized points internally. .. video:: _static/movies/mllearnsinput.mp4 :width: 100% | |