Reinforcement learning for neural architecture search: A review

Abstract

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 doesnt 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.

The Transition From Intelligent to Affective Tutoring System: A Review and Open Issues

“…At first, from the above CI approaches discussion, NNs seem quite popular in understanding the complex patterns with satisfactory computation performance. The authors [149] provided several progressive RL methods in NNs architectural task with challenges for further consideration. Merging the power of NNs with RL in the educational domain (i.e., devising an ITS or ATS) will be a novel approach to explore.…”

Toward Intelligent Industrial Informatics: A Review of Current Developments and Future Directions of Artificial Intelligence in Industrial Applications

“…This inclusive capability should be further explored beyond supervised learning, focusing on unsupervised, one-shot, reinforcement and transfer learning tasks. On the other hand, the increasing prevalence of sub-optimal deep learning neural network models indicates that the development of meta-learning techniques for optimised model configuration is an emerging need [112]. In Industrial Electronics, this should potentially lead to new meta-learning techniques specific to each industrial domain.…”

Microgeneration of Wind Energy for Micro and Small Businesses: Application of ANN in Sensitivity Analysis for Stochastic Economic Feasibility

“…The use of ANS allows for the creation and testing of neural networks for data analysis and prediction problems. It designs a number of networks to solve the problem and then selects those networks that best represent the relationship between the input and target variables (for more, see [83]- [84]).…”