NA / 5
We will cover the following tasks in 41 minutes:
Introduction and Overview
In order to better understand our problem, we need to look at the data. So in this task, we create a new experiment in Azure ML Studio and import our data. The data used in this experiment is a popular MNIST dataset which consists of 70,000 grayscale images of hand-written digits.
Once we have imported the data, we can begin pre-processing it. We will use the Edit Metadata module to convert the class labels to categorical feature types.
Next, we can use the Split Data module to partition the rows of our dataframe into a 70% training split and a 30% test split. We are now ready to use the data to train and evaluate our neural network model.
Train and Evaluate Multiclass Neural Network
In this task, we demonstrate the usage of the Multiclass Neural Network module to train a neural network that can be used to predict a target having multiple values. We will start with the most basic type of neural network: one hidden layer, fully connected.
Create and Deploy Predictive Web Service
Once we’ve trained our neural network model, we’re ready to convert our training experiment into a predictive experiment to score new data.
By converting to a predictive experiment, we’re getting our trained model ready to be deployed as a scoring web service. Users of the web service can send input data to our model and our model will send back the prediction results. As we convert to a predictive experiment, keep in mind how you expect your model to be used by others.
Now that the predictive experiment has been prepared, we can deploy it as a new (Resource Manager-based) Azure web service. Using the web service, users can send data to our model and the model will return its predictions.
Inference Using the Web Service API
To test our new web service, click Test web service under common tasks. On the Test page, we can test our web service as a Request-Response Service (RRS) or a Batch Execution service (BES).
Now that our web service is deployed from Machine Learning Studio, we can send new data to the service and receive responses programatically. Using our web service API key and other authenticating information, we will build a Python web app to send data about handwritten digits to our web service and receive the results.
About the Host (Snehan Kekre)
Snehan Kekre is a Machine Learning and Data Science Instructor at Coursera. He studied Computer Science and Artificial Intelligence at Minerva Schools at KGI, based in San Francisco. His interests include AI safety, EdTech, and instructional design. He recognizes that building a deep, technical understanding of machine learning and AI among students and engineers is necessary in order to grow the AI safety community. This passion drives him to design hands-on, project-based machine learning courses on Rhyme.