This chapter was not a typical one in this book because we discussed more theory than practical data augmentation techniques. At first, the link between data biases and data augmentation seems tenuous. Still, as you begin to learn about computational, human, and systemic biases, you see the strong connection because they all share the same goal of ensuring successful ethical AI system usage and acceptance.
In other words, data augmentation increases the AI’s prediction accuracy while reducing the data biases in augmenting, ensuring the AI forecast has fewer false-negative and true-negative outcomes.
The computational, human, and systemic biases are similar but are not mutually exclusive. However, providing plenty of examples of real-world biases and observing three real-world image datasets and two real-world text datasets made these biases easier to understand.
The nature of data bias in augmenting makes it challenging to compute biases programmatically. However...