AIExplainer
Machine Learning Mathematics Intermediate 2 min read

What is a feature vector?

The array of feature values comprising an example.

The array of feature values comprising an example. The feature vector is input during training and during inference. For example, the feature vector for a model with two discrete features might be:

Each example supplies different values for the feature vector, so the feature vector for the next example could be something like:

Feature engineering determines how to represent features in the feature vector. For example, a binary categorical feature with five possible values might be represented with one-hot encoding. In this case, the portion of the feature vector for a particular example would consist of four zeroes and a single 1.0 in the third position, as follows:

As another example, suppose your model consists of three features: - a binary categorical feature with five possible values represented with one-hot encoding; for example:`[0.0, 1.0, 0.0, 0.0, 0.0]` - another binary categorical feature with three possible values represented with one-hot encoding; for example:`[0.0, 0.0, 1.0]` - a floating-point feature; for example:`8.3`. In this case, the feature vector for each example would be represented by nine values. Given the example values in the preceding list, the feature vector would be:

See Numerical data: How a model ingests data using feature vectors in Machine Learning Crash Course for more information.