Fig. 2: Learning procedure. | Communications Biology

Fig. 2: Learning procedure.

From: Mutual generation in neuronal activity across the brain via deep neural approach, and its network interpretation

Fig. 2

The figure depicts how the loss on the training data and the loss on the validation data decreases as the multilayer LSTM model is trained. A decrease in loss indicates that the training of the Multilayer LSTM has progressed. The loss, common to both data, decreases sharply at 25–100 epochs. However, the precision of the firing rate and the reproducibility of synchronous firing continued to improve up to 350 epochs.

Back to article page