Fig. 22
From: Towards a robust out-of-the-box neural network model for genomic data
Accuracy of LSTM-AE+NN model [32] with three different batch sizes (32, 256 and 1024) on three datasets of increasing size. There is no evidence of overfitting with this model, and accuracy seems to decrease as the data size increases with the largest data (motif discovery) having the smallest accuracy (barely above 50%)