Neural networks are the most important technique for machine learning and artificial intelligence. They are dramatically improving the state-of-the-art in energy, marketing, health, and many other domains.
This tutorial describes the principal applications and concepts related to neural networks.

1. Model types

The most common learning tasks for neural networks are approximation, classification, and forecasting.

2. Data set

The data set contains the information available for creating the model.

3. Neural network

The neural network represents the approximation or classification model.

4. Training strategy

The training strategy fits the neural network with the data set.

5. Model selection

Model selection algorithms look for the neural network architecture with the best generalization capabilities.

6. Testing analysis

The testing analysis compares the outputs from the neural network against the targets in an independent set.

7. Model deployment

Model deployment is used to apply a model to predict new data.

In the following pages, we describe each of these concepts in detail.
 Model Types ›