The next few sections will describe the NAS framework. You will learn about how the framework learns to generate other neural networks to complete tasks using a popular reinforcement learning scheme called REINFORCE, which is a type of policy gradient algorithm.
Neural Architecture Search
Generating and training child networks
Research on algorithms that generate neural architectures has been around since the 1970's. What sets NAS apart from previous works is its ability to cater to large-scale deep learning algorithms and its formulation of the task as a reinforcement learning problem. More specifically, the agent, which we will refer to as the Controller, is a recurrent neural network that generates a sequence of values...
