Depth Self-Optimized Learning Toward Data Science
This addresses the challenge of manual hyperparameter tuning in machine learning for data scientists, but it appears incremental as it builds on existing reinforcement learning methods for neural architecture search.
The paper tackles the problem of automating artificial neural network (ANN) depth configuration and optimization without manual intervention, proposing a two-stage model called Depth Self-Optimized Learning (DSOL) that uses reinforcement learning to optimize depth, and reports that it performed well on Iris and Boston housing datasets.
We propose a two-stage model called Depth Self-Optimized Learning (DSOL), which aims to realize ANN depth self-configuration, self-optimization as well as ANN training without manual intervention. In the first stage of DSOL, it will configure ANN of specific depth according to a specific dataset. In the second stage, DSOL will continuously optimize ANN based on Reinforcement Learning (RL). Finally, the optimal depth is returned to the first stage of DSOL for training, so that DSOL can configure the appropriate ANN depth and perform more reasonable optimization when processing similar datasets again. In the experiment, we ran DSOL on the Iris and Boston housing datasets, and the results showed that DSOL performed well. We have uploaded the experiment records and code to our Github.