Designing Neural Network Architectures using Reinforcement Learning

Understand

At present, designing convolutional neural network (CNN) architectures requires both human expertise and labor.

• New architectures are handcrafted by careful experimentation or modified from a handful of existing networks.
• We introduce MetaQNN, a meta-modeling algorithm based on reinforcement learning to automatically generate high-performing CNN architectures for a given learning task.
• The learning agent is trained to sequentially choose CNN layers using $Q$-learning with an $\epsilon$-greedy exploration strategy and experience replay.