Multivariate Calibration Approach for Quantitative Determination of Cell-Line Cross Contamination by Intact Cell Mass Spectrometry and Artificial Neural Networks - Fig 3

(A) Optimal ANN architecture (one Input layer, one Hidden layer with four neurons, and one Output layer). (B) Training and leave-one-out verification plot of the RMS versus the number of training cycles (epochs). First 50 000 iterations are shown. The inset shows a detailed plot for the first 10 000 training cycles.