Skip to main content
. 2020 Jul 9;2(2):fcaa096. doi: 10.1093/braincomms/fcaa096

Figure 3.

Figure 3

An Artificial Neural Network example: here is a schematic overview of how high-dimensional genetics and brain imaging is used in a deep-learning model to make a probabilistic estimate (p) whether people are likely to develop epilepsy (red node) or not (green node). The lines between layers represent connections, each associated with a weight-adjusted during feed-forward training and updated during back-propagation until the optimal model performance.