From: DeepGene: an advanced cancer type classifier based on deep learning and somatic point mutations
Input: Gene data matrix A ∈ {0, 1}m × n after CGF and ISR, where rows and columns correspond to samples and genes, respectively; max training epoch E max. 1: Training: for each training epoch e ≤ E max:  (a) For each sample a i  = A(i, :):   i. Conduct feed-forwarding and compute the loss J;   ii. Conduct back-propagation to update the W and b 2: Testing: for each sample a i  = A(i, :):  (a) Conduct feed-forwarding and get softmax probability P;  (b) Adopt the cancer type correspond to max(P) as the result of a i . Output: Trained network model (training) or classification results for the samples (testing). |