RNNTestCore

scalation.modeling.autograd.RNNTestCore
object RNNTestCore

The RNNTestCore object defines a suite of @main entrypoints that exercise the autograd system using recurrent neural network components. These tests verify:

  • forward computation consistency for RNNCell and GRUCell
  • correct propagation of hidden states through RNNBase
  • correctness of gradient backpropagation through time
  • multilayer RNN/GRU behavior and parameter interaction
  • construction and export of autograd computation graphs for debugging All tests use synthetic inputs and manually assigned weights/biases to ensure deterministic behavior to validate against PyTorch, enabling reliable gradient-checking via finite differences using GradCheck.gradCheck.

Attributes

Note

This file focuses exclusively on core autograd correctness and does not contain any real-data forecasting experiments.

Graph
Supertypes
class Object
trait Matchable
class Any
Self type

Members list

Value members

Concrete methods

def gruCellTest(): Unit

The gruCellTest main function tests the GRUCell class.

The gruCellTest main function tests the GRUCell class.

runMain scalation.modeling.autograd.gruCellTest

Attributes

def gruMultiLayerTest(): Unit

The gruMultiLayerTest main function tests the GRU class.

The gruMultiLayerTest main function tests the GRU class.

runMain scalation.modeling.autograd.gruMultiLayerTest

Attributes

def rnnBaseTest(): Unit

The rnnBaseTest main function tests the RNNBase class.

The rnnBaseTest main function tests the RNNBase class.

runMain scalation.modeling.autograd.rnnBaseTest

Attributes

def rnnCellTest(): Unit

The rnnCellTest main function tests the RNNCell class.

The rnnCellTest main function tests the RNNCell class.

runMain scalation.modeling.autograd.RnnTest.rnnCellTest

Attributes

def rnnMultiLayerTest(): Unit

The rnnMultiLayerTest main function tests the RNN class.

The rnnMultiLayerTest main function tests the RNN class.

runMain scalation.modeling.autograd.rnnMultiLayerTest

Attributes