Skip to main content
. Author manuscript; available in PMC: 2024 May 1.
Published in final edited form as: Trends Immunol. 2023 Mar 30;44(5):333–344. doi: 10.1016/j.it.2023.03.002

Figure 2. Comparison of common machine learning and deep learning models.

Figure 2.

A. Examples of common classical machine learning algorithms. Algorithms are a mix of supervised approaches, such as linear regression, logistic regression, random forest, and support vector machines, in which the models are trained and tested on labelled data, and unsupervised algorithms, such as principal component analysis and K-means, in which the algorithm uses unlabeled data. B. Examples of common deep learning model architectures and associated tasks. Deep learning architectures pass information among nodes within layers to create more abstract data representations that can result in more accurate model predictions. Deep learning models generally have greater performance than machine learning algorithms however are generally more complex to create and are computationally more expensive. This figure was created using BioRender (https://biorender.com/)