Two sets of layers. On the left, an empty layer transforms into a block of pixels, which then changes back into an empty layer. On the right, a blurred image gradually transforms into a block of pixels and ultimately appears to show a head attached to a body. The left and right layers are labeled with context and without context, respectively.

Fig. 4

The weights of small kernels in hidden layers (here 5 × 5) can be really difficult to interpret alone. Here some context allows better understanding how it modulates the interaction between concepts conveyed by the input and the output. (Adapted from [8] (CC BY 4.0))

From: Chapter 22, Interpretability of Machine Learning Methods Applied to Neuroimaging

Cover of Machine Learning for Brain Disorders
Machine Learning for Brain Disorders [Internet].
Colliot O, editor.
New York, NY: Humana; 2023.
Copyright 2023, The Author(s)

Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

The images or other third party material in this chapter are included in the chapter's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

NCBI Bookshelf. A service of the National Library of Medicine, National Institutes of Health.