Documentation ¶
Overview ¶
Implementation of the MIST (MIxed hiSTory) recurrent network as described in "Analyzing and Exploiting NARX Recurrent Neural Networks for Long-Term Dependencies" by Di Pietro et al., 2018 (https://arxiv.org/pdf/1702.07805.pdf).
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Model ¶
type Model struct { Wx *nn.Param `type:"weights"` Wh *nn.Param `type:"weights"` B *nn.Param `type:"biases"` Wax *nn.Param `type:"weights"` Wah *nn.Param `type:"weights"` Ba *nn.Param `type:"biases"` Wrx *nn.Param `type:"weights"` Wrh *nn.Param `type:"weights"` Br *nn.Param `type:"biases"` // contains filtered or unexported fields }
Model contains the serializable parameters.
type Processor ¶
type Processor struct { nn.BaseProcessor States []*State // contains filtered or unexported fields }
func (*Processor) Forward ¶
Forward performs the forward step for each input and returns the result.
func (*Processor) SetInitialState ¶
Click to show internal directories.
Click to hide internal directories.