Machine Intelligence : Demystifying Machine Learning, Neural Networks and Deep Learning

2.3 Evaluating a Machine Learning Model

Nature of the problem (Regression, Classification, Clustering, etc.) – Number of data records available for training – Decision support or cognitive use case? – Need for explain-ability

Number of data records available can also influence the choice of the machine learning algorithm. Machine learning algorithms like support vector machines (SVM) can work with fewer training records whereas neural networks and deep learning algorithms require large amounts of data to be able to train the model effectively.

Model/Ensemble Section:

2.2 Project Methodology

decision support use cases predominantly work with structured data as input whereas cognitive use cases work with unstructured data.

Cognitive Use Cases:

Decision Support Use Cases:

Based on the above description, we can classify machine learning use cases into 2 categories: – Decision support use cases – Cognitive use cases