Fig. 1: Example neural network architectures. | npj Breast Cancer

Fig. 1: Example neural network architectures.

From: Biological insights and novel biomarker discovery through deep learning approaches in breast cancer histopathology

Fig. 1

a Basic neural network demonstrating input nodes with dimensionality of 8, two hidden layers that involve dimension expansion and subsequent reduction with a final output node. Each input node is connected to each of the hidden nodes (a fully connected network), with lines connecting nodes representing weights applied to a source to reach a destination. The above representation can also be visualized as a weight matrix, translating from the dimensionality of the input nodes to the dimensionality of the output nodes. b A pictorial the training process – inputs are fed to a DL network, predictions are made and compared to ground truth labels and parameters are updated in a loop. c A convolutional network architecture demonstrating the typical backbone of pooling layers followed by convolutional layers. Note that convolutions increase the number of filters while reducing dimensionality in the x/y dimensions (https://alexlenail.me/NN-SVG/).

Back to article page