Fig. 24From: Towards a robust out-of-the-box neural network model for genomic dataROC curves of LSTM-AE+NN model [32] with three different batch sizes (32, 256 and 1024) on three datasets of increasing size. The higher the curve, the better performance with a 45\(^{\circ }\) dashed line to represent random prediction. The splice data has three panels since ROC curves assume binary classification and the splice dataset has three classes (0, 1, 2). Each panel corresponds to prediction one class vs the other two combined. Again, we see no differences with respect to batch size and ROC curves close to the 45\(^{\circ }\) dashed line (random prediction) for the motif discovery dataBack to article page