Table 2 The hyperparameters for the CNN, RNN, and Tree-RNN.

From: Neuron type classification in rat brain based on integrative convolutional and tree-based recurrent neural networks

CNN

RNN

Tree-RNN

lr-fc = 1e-4

lr = 1e-4

lr = 1e-4

lr-conv = 1e-5

n-hidden = 128

n-hidden = 128

Epochs = 20

Epochs = 100

Epochs = 100

Batch-size = 300

Batch-size = 400

Batch-size = 500

Optimizer = Adam

Maxlen-of-tree = 1500

Maxlen-of-tree = 1500

Loss = CrossEntropyLoss

OverallHeight

in-dim = 7

Back to article page