Automated data processing and feature engineering for deep learning and big data applications: a survey

arXiv:2403.11395v1 Announce Type: new
Abstract: Modern approach to artificial intelligence (AI) aims to design algorithms that learn directly from data. This approach has achieved impressive results and has contributed significantly to the progress of AI, particularly in the sphere of supervised deep learning. It has also simplified the design of machine learning systems as the learning process is highly automated. However, not all data processing tasks in conventional deep learning pipelines have been automated. In most cases data has to …

abstract algorithms applications artificial artificial intelligence arxiv automated big big data contributed cs.ai cs.db cs.lg data data applications data processing deep learning design engineering feature feature engineering intelligence learn modern processing progress results sphere survey type