Machine learning versus deep learning
| Features | Machine learning | Deep learning |
|---|---|---|
| Data setting | Structured | Not structured |
| Learning | By operator | Intrinsic |
| Database | < 1 × 108 data points | > 1 × 108 data points |
| Algorithm | Variable | Artificial neural network |
| Problem solving | By partitioning | End-to-end approach |
| Execution time | Long model test time | Short model test time |
| Application field | Routine operations | Complex systems |
| Hardware | Low-end machine | High-end machine |
| Suitability | Simple problems | Complex problems |
I thank Dr. Matteo R. Ronchi (Caltech, Pasadena, USA) and Dr. Joseph L. Marino (DeepMind, London, UK) for inspiring this work, critically reading the text, and, most of all, for providing insightful discussions that deepened and broadened my understanding of machine learning.
The author contributed solely to the work.
The author declares that she has no conflicts of interest.
Not applicable.
Not applicable.
Not applicable.
Not applicable.
The author’s research is supported by FATALSDRUG Project [Progetti di Ricerca@CNR SAC.AD002.173.058] from National Research Council, Italy. The funder had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
© The Author(s) 2023.