Backpropagate: Run backpropagation for a single layer. In backpropagation, a...

In ncats/MultiOmicsGraphPrediction: Network-Based Ensemble Prediction from IntLIM Predictors

Run backpropagation for a single layer. In backpropagation, a gradient is is computed by taking partial derivatives for each of the model weights. Given a learning rate, the weights are adjusted according to the gradient.

Description

Run backpropagation for a single layer. In backpropagation, a gradient is is computed by taking partial derivatives for each of the model weights. Given a learning rate, the weights are adjusted according to the gradient.

Usage

Backpropagate(
  modelResults,
  prunedModels,
  Y.pred,
  minCutoff,
  maxCutoff,
  useCutoff = FALSE,
  weights,
  averaging = FALSE
)

Arguments

modelResults	An object of the ModelResults class.
prunedModels	The models that remain after pruning.
Y.pred	The predicted phenotype value.
minCutoff	Mininum cutoff for the prediction.
maxCutoff	Maximum cutoff for the prediction.
useCutoff	Whether or not to use the cutoff for prediction. Default is FALSE.
weights	The current value of the weights
averaging	If TRUE, then averaging is used to combine predictors rather than retaining the same functional form for both the input and the output.

ncats/MultiOmicsGraphPrediction documentation built on Aug. 23, 2023, 9:19 a.m.