Summary
In this chapter, we gave a short description of the main techniques used in artificial intelligence, one based on symbolic reasoning and one based on neural networks and other numeric techniques.
Then, we explained the basic principles behind machine learning and described various kinds of learning, and then focused on supervised learning and discussed how to verify if we have enough examples for our learning task.
Later, we described in more detail learning techniques adequate for learning smooth functions, focusing on neural networks and on the support vector algorithm, and then techniques based on induction.
Then we presented four steps to turn machine learning projects into practical software solutions, especially using the Azure Machine Learning service.
Finally, we presented an alternative to Azure Machine Learning – using ML.NET, especially by using ML.NET Model Builder, which is a great tool for easily creating models for console and API predictions...