Azure Machine Learning designer gives you a cloud-based interactive, visual workspace that you can use to easily and quickly prep data, train and deploy machine learning models. It supports Azure Machine Learning compute, GPU or CPU. Azure Machine Learning designer also supports publishing models as web services on Azure Kubernetes Service that can easily be consumed by other applications. To use Azure Machine Learning designer, you do not need programming experience and this quickstart will walk you through an exercise that will show how to process training data, create a model, train, score, and evaluate the model and finally deploy the trained model as a web service.
Concept 9 - The Models
Lab 1: Use an algorithm (linear regression) to train a model
Concept 1 - Data Import and Transformation
Lab 2: Import, transform, and export data
Concept 2 - Manage Data
Lab 3: Create and version a dataset
Lab 4: Engineer and select features
Concept 3 - Model Training Basics
Lab 5: Train and evaluate a model
Concept 4 - Ensembles
Lab 6: Train a two-class decision forest
Lab 7: Train a simple classifier with Automated ML
Concept 1 - Supervised Learning, Classification
Lab 8: Compare the performance of the various two-class classifiers
Lab 9: Compare the performance of the various multiclass classifiers
Concept 2 - Classifier using Automated Machine Learning
Lab 10: Train a classifier using automated machine learning
Concept 3 - Supervised Learning, Regression
Lab 11: Compare the performance of the various regressors
Concept 4 - Regression using Automated Machine Learning
Lab 12: Train a regressor using automated machine learning
Concept 6 - CLustering
Lab 13: Train a simple clustering model
Concept 1 - A taste of deep learning
Lab 14: Classical ML vs. Deep Learning: multiclass neural net module
Concept 3 - Similarity learning recommendation
Lab 15: Train a simple recommender
Concept 4 - Text classification
Lab 16: Train a simple text classifier
Concept 7 - Forecasting
Lab 17: Train a time-series forecasting model using automated machine learning
Concept 2 - Compute Resources
Lab 18: Managing compute
Lab 19: Train a machine learning model from a managed notebook environment
Concept 3 - Basic Modeling
Lab 20: Explore experiments and runs
Concept 5 - Operationalizing Models
Lab 21: Deploy a trained model as a webservice
Concept 6 - Programatically Accessing Managed Services
Lab 22: Training and deploying a model from a notebook running in a Compute Instance
Concept 2 - Model transparency and explainability
Lab 23: Explore model explanations