Automated deep learning (AutoDL) is the process of automating the process of applying deep learning to real-world problems. AutoDL covers the complete pipeline from the raw dataset to the deployable deep learning model. AutoDL was proposed as an artificial intelligence-based solution to the ever-growing challenge of applying deep learning. The high degree of automation in AutoDL allows non-experts to make use of deep learning models and techniques without requiring to become an expert in this field first.
Automating the process of applying deep learning end-to-end additionally offers the advantages of producing simpler solutions, faster creation of those solutions, and models that often outperform hand-designed models.