GTNs are a novel approach to improve the training of machine learning models using synthetic data.
In the GTN model, the generator produces completely new artificial data that a never-seen-before learner neural network (with a randomly sampled architecture and weight initialization) trains on for a small number of learning steps.
The core principle of Uber’s GTNs is based on a simple and yet radical idea: allowing machine learning to create the training data itself.
These two ideas: selecting the best examples from a training set and understanding how a neural network learns were the foundation of Uber’s creative method for training machine learning models.
A common analogy in artificial intelligence(AI) circles is that training data is the new oil for machine learning models.