- addInputs
Specify the inputs to the network, and their associated labels.
- addLayer
Add a layer, with no InputPreProcessor, with the specified name and specified
inputs.
- build
Create the ComputationGraphConfiguration from the Builder pattern
- setOutputs
Set the network output labels. These should be the names of the OutputLayer
instances in the network
- addVertex
Add a GraphVertex to the network configuration. A GraphVertex defines forward
and backward pass meth
- setInputTypes
Specify the types of inputs to the network, so that:
(a) preprocessors can be automatically added, a
- backprop
Whether to do back prop (standard supervised learning) or not
- pretrain
Whether to do layerwise pre training or not
- backpropType
The type of backprop. Default setting is used for most networks (MLP, CNN etc),
but optionally trunc
- tBPTTBackwardLength
When doing truncated BPTT: how many steps of backward should we do?
Only applicable when doing backp
- tBPTTForwardLength
When doing truncated BPTT: how many steps of forward pass should we do before
doing (truncated) back
- <init>