Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: CancerNet: a unified deep learning network for pan-cancer diagnostics

Fig. 1

The CancerNet architecture. Methylation data are input to the encoder. The encoder is composed of two dense feedforward layers using the Relu activation function. Output of the encoder is passed to the probabilistic layer, which passes its output to the classifier and generator/decoder. The classifier is two dense feedforward layers, the first with the ReLu activation function and the second with the softmax activation function. The decoder is two dense feedforward layers, the first using the Relu activation and the second using the sigmoid activation

Back to article page