Plant Phenomics / 2021 / Article / Tab 2

Research Article

Qualification of Soybean Responses to Flooding Stress Using UAV-Based Imagery and Deep Learning

Table 2

FNN model parameters used to classify the FISs.

ParametersDefinitionValue

hiddenSizesThe number of hidden layers10
trainFcnTraining functiontrainlm
EpochsMaximum number of epochs to train1000
GoalPerformance goal0
max_failMaximum validation failures6
min_gradMinimum performance gradient1e-7
muInitial learning rate0.001
mu_decDecrease factor for the learning rate0.1
mu_incIncrease factor for the learning rate10
mu_maxIncrease factor for the learning rate1e10