Machine Learning Tutorial

What is Machine Learning? Machine Learning Life Cycle Python Anaconda setup Difference between ML/ AI/ Deep Learning Understanding different types of Machine Learning Data Pre-processing Supervised Machine Learning

ML Regression Algorithm

Linear Regression

ML Classification Algorithm

Introduction to ML Classification Algorithm Logistic Regression Support Vector Machine Decision Tree Naïve Bayes Random Forest

ML Clustering Algorithm

Introduction to ML Clustering Algorithm K-means Clustering Hierarchical Clustering

ML Association Rule learning Algorithm

Introduction to association Rule Learning Algorithm


Top 5 programming languages and their libraries for Machine Learning Basics Vectors in Linear Algebra in ML Decision Tree Algorithm in Machine Learning Bias and Variances in Machine Learning Machine Learning Projects for the Final Year Students Top Machine Learning Jobs Machine Learning Engineer Salary in Different Organisation Best Python Libraries for Machine Learning Regularization in Machine Learning Some Innovative Project Ideas in Machine Learning What is Cross Compiler Decoding in Communication Process IPv4 vs IPv6 Supernetting in Network Layer TCP Ports TCP vs UDP TCP Working of ARP Hands-on Machine Learning with Scikit-Learn, TensorFlow, and Keras Kaggle Machine Learning Project Machine Learning Gesture Recognition Machine Learning IDE Pattern Recognition and Machine Learning a MATLAB Companion Chi-Square Test in Machine Learning Heart Disease Prediction Using Machine Learning Machine Learning and Neural Networks Machine Learning for Audio Classification Standardization in Machine Learning Student Performance Prediction Using Machine Learning

Azure Machine Learning

Machine learning algorithms are powerful methods and techniques which are high in terms of probability and used to give computers high power to compute the solution for large numbers of datasets.

Computers generally use the previous dataset’s result and then compute the huge, complex current dataset referencing previous datasets.


Azure is Microsoft's cloud computing platform which is also called Windows Azure. On this platform, we can develop various cloud services like computation, networking, storage, IoT, AI, etc.

Azure Machine Learning

With the help of Azure Machine Learning services, developers can create, train or migrate their machine learning models on cloud networks on a larger scale. It has many inbuilt libraries support like Matplotlib, Scikit-learn or TensorFlow, etc.

We can deploy trained machine learning models on Azure Kubernetes.

Azure Machine learning architecture

Any machine learning model on azure follows the steps given below:

  • Python is used to create your machine learning training program, after which you should set up a compute target.
  • To run the program in this environment, place it in the computed target. The program can be read from or written to a datastore at the time of training. The workspace's workspace stores the running records as runs. Within experiments, they are grouped.
  • Ask a question about the tests. For logged metrics from recent and previous executions, it is carried out. Repeat all the steps starting with the first one if the metrics do not produce the desired output. Then, if the result was pertinent, register your model. This is carried out within the model registry.
  • Make a program for scoring.
  • Make a picture. Add this picture to the image database.
  • Deploy this image in Azure at the end. It's made available as a web service.


A model is a piece of code that receives input and produces results. The selection of algorithms, providing data, and fine-tuning of hyper parameters are all necessary when creating a machine learning model. A trained model inherits what it has learned from the training process thanks to the iterative nature of training.

Executing in Azure Machine Learning produces a model. You can still use the model that you built by training it outside of Azure Machine Learning, so don't worry. Simply registering it in the Azure Machine Learning service workspace is all that is necessary.


The image gives you a setting in which to independently deploy your model. It has every element the model calls for. An image comprises dependencies needed by your model or script, a model, an application, or a script (this script is supplied as an input to the model, which provides an output).

FPGA and Docker images are the two types of images available for Azure machine learning. When installing a field-programmable gate array in Azure ML, an FPGA image is used, and when deploying computer targets like Azure Kubernetes Service or Azure Container Instances, a Docker image is utilized.


Your picture is instantiated as a web service through a deployment that is then hosted in the cloud. Additionally, it has the ability to instantiate an image into an IoT module for use in the deployment of integrated devices.


Your Azure account's datastore offers a storage abstraction. The data is stored via the Azure file share and Azure blob container. A default datastore is kept by each workspace. Other data storage can be requested and registered here. The Python SDK API is required to retrieve this data. The Azure Machine Learning CLI can also be used to get files from this location.


The process involved in machine learning phases is created and managed by a machine learning pipeline. For instance, a pipeline can perform operations like data preparation, deployment, model training, and inferencing. Every step in the pipeline's several phases runs separately on different compute targets.

Compute target

It is a computational resource that is employed when running your deployment-related training course or hosting service. Workspaces are connected to compute targets. Other than the local machine, compute targets are shared among workspace users.


The directory containing the script is compressed by Azure Machine Learning when the run is supplied. The compute target receives this zip file which is subsequently extracted and run there. This file is kept as a snapshot by Azure Machine Learning so that you may access the run history. This snapshot, which is available in a run record, is simple to obtain.