Scientific Programming / 2019 / Article / Tab 7

Research Article

Software Defect Prediction via Attention-Based Recurrent Neural Network

Table 7

Tuned parameters for DP-ARNN.

ParameterDescription (value)

Embedding_dimThe dimensionality of embedding vectors (30)
Vector_lengthThe length of each AST vector (2000)
Bi-LSTM unitsThe number of the Bi-LSTM units per layer (40)
1st hidden layer nodesThe number of 1st hidden layer nodes (16)
2nd hidden layer nodesThe number of 2nd hidden layer nodes (24)
Batch_sizeThe number of training samples that propagated through DP-ARNN at a time (32)
EpochOne forward/backward pass of all the training samples (20)
MonitorThe evaluation criteria on the validation set (val_acc)
Loss functionThe loss function to minimize (binary_crossentropy)
OptimizerThe loss function solver (RMSprop)
ActivationTypes of activation used in fully connected layers (tanh, linear, and sigmoid)

We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at help@hindawi.com to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19. Sign up here as a reviewer to help fast-track new submissions.