A Review of Meta-Reinforcement Learning for Deep Neural Networks Architecture Search
This is an incremental survey paper summarizing existing research on automating CNN architecture design for computer vision tasks.
This survey reviews current progress in automating convolutional neural network architecture search, which addresses the problem that manual design requires significant human expertise and computation time without guaranteeing optimal networks.
Deep Neural networks are efficient and flexible models that perform well for a variety of tasks such as image, speech recognition and natural language understanding. In particular, convolutional neural networks (CNN) generate a keen interest among researchers in computer vision and more specifically in classification tasks. CNN architecture and related hyperparameters are generally correlated to the nature of the processed task as the network extracts complex and relevant characteristics allowing the optimal convergence. Designing such architectures requires significant human expertise, substantial computation time and doesn't always lead to the optimal network. Model configuration topic has been extensively studied in machine learning without leading to a standard automatic method. This survey focuses on reviewing and discussing the current progress in automating CNN architecture search.