Deep learning gained a lot of traction in the machine learning community. The performance of these models often surpasses other more classical approaches. Deep learning detractors often point to the lack of interpretability of the complex neural networks and to the, sometimes unrealistic, amount of data needed to train them properly. This chapter provides a basic layout of the inner working of deep learning models and links then to classical neural networks. Furthermore, we review the current and potential application of this approach in the field of chemometrics.
|Title of host publication||Comprehensive Chemometrics|
|Subtitle of host publication||Chemical and Biochemical Data Analysis|
|Editors||Steven Brown, Roma Tauler, Beata Walczak|
|Number of pages||17|
|Publication status||Published - 2020|