Figure 3 | Scientific Reports

Figure 3

From: A convolutional recurrent neural network with attention for response prediction to repetitive transcranial magnetic stimulation in major depressive disorder

Figure 3

Block diagram of the TL-BLSTM and TL-BLSTM-attention model. Each five sequential RGB images create a video sample which will be fed into the TL models. A sequence of spatial features of each input image can be used as input to the recurrent model. Dashed block represents the attention block which can be added as an additional layer to the TL-BLSTM model to create the TL-BLSTM-attention model.

Back to article page