- What is Machine Learning?
- What is Deep Learning?
- What is Azure ML?
- Steps to Perform Image Classification in Azure ML (Python SDK).
What is Machine Learning?
Machine Learning is the application of Artificial Intelligence that focuses on the development of computer programs, through which it can constantly learn to perform tasks.
Click here to know more about Machine Learning.
What is Deep Learning?
Deep Learning is the subset of Machine Learning, which imitates the functionality of the human brain to learn and perform tasks.
Deep Learning is also called deep neural networks, and the most popular type of deep neural network is convolutional neural networks (CNN)
Convolutional neural Network:
CNN is mostly used for image recognition. Images are simply a matrix of values corresponding to the intensity of light at each pixel value.
A filter that examines the subset of the matrix and eventually it covers all the values in the matrix. The output of the convolution layer is called a feature map.
A pooling layer compresses the spatial information of the feature map.
Max pooling returns the maximum value of each scanning window.
What is Azure ML?
Azure Machine Learning, is a cloud-based environment used to train, deploy, automate, manage, and track ML models.
Azure Machine Learning helps us to perform classical Machine Learning to Deep Learning.
Azure provides two modes to perform ML
- No-code/low-code mode-ML designer
The Azure Machine Learning designer:
This provides the user a drag and drop facility to train and deploy the ML pipeline.
Note: This does not involve any kind of coding.
One can use Jupyter Notebooks to write a custom code (R or python) to create a Machine Learning model.
Malaria cell Image dataset is a popular open-source data is chosen to perform CNN using Azure ML.
The sole purpose of this activity is to understand, how to do Deep Learning /Machine Learning in the Azure Platform.
Data can be downloaded from the link.
Dataset is also available in TensorFlow -tdfs.image_classification.Malaria
Link for the next part: click here