tpr

Documentation

Index

• type Model
  • func New(in, nSymbols, dSymbols, nRoles, dRoles int) *Model
  • func (m *Model) Forward(xs ...ag.Node) []ag.Node
  • func (m *Model) LastState() *State
  • func (m *Model) SetInitialState(state *State)
• type State

Types

type Model

type Model struct {
	nn.BaseModel
	WInS   nn.Param `spago:"type:weights"`
	WInR   nn.Param `spago:"type:weights"`
	WRecS  nn.Param `spago:"type:weights"`
	WRecR  nn.Param `spago:"type:weights"`
	BS     nn.Param `spago:"type:biases"`
	BR     nn.Param `spago:"type:biases"`
	S      nn.Param `spago:"type:weights"`
	R      nn.Param `spago:"type:weights"`
	States []*State `spago:"scope:processor"`
}

Model contains the serializable parameters.

func New

func New(in, nSymbols, dSymbols, nRoles, dRoles int) *Model

New returns a new model with parameters initialized to zeros.

func (*Model) Forward

func (m *Model) Forward(xs ...ag.Node) []ag.Node

Forward performs the forward step for each input node and returns the result.

func (*Model) LastState

func (m *Model) LastState() *State

LastState returns the last state of the recurrent network. It returns nil if there are no states.

func (*Model) SetInitialState

func (m *Model) SetInitialState(state *State)

SetInitialState sets the initial state of the recurrent network. It panics if one or more states are already present.

type State

type State struct {
	AR ag.Node
	AS ag.Node
	S  ag.Node
	R  ag.Node
	Y  ag.Node
}

State represent a state of the TPR recurrent network.