mist

Documentation

Overview

Package mist provides an 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

• type Model
  • func New(in, out, numOfDelays 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
	Wx          nn.Param `spago:"type:weights"`
	Wh          nn.Param `spago:"type:weights"`
	B           nn.Param `spago:"type:biases"`
	Wax         nn.Param `spago:"type:weights"`
	Wah         nn.Param `spago:"type:weights"`
	Ba          nn.Param `spago:"type:biases"`
	Wrx         nn.Param `spago:"type:weights"`
	Wrh         nn.Param `spago:"type:weights"`
	Br          nn.Param `spago:"type:biases"`
	NumOfDelays int
	States      []*State `spago:"scope:processor"`
}

Model contains the serializable parameters.

func New

func New(in, out, numOfDelays 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 {
	Y ag.Node
}

State represent a state of the MIST recurrent network.