The highest tagged major version is
Documentation
¶
Index ¶
- func Logistic(x, a float64) float64
- func Normal(stdDev, mean float64) float64
- func Uniform(stdDev, mean float64) float64
- type ActivationType
- type BinaryCrossEntropy
- type Config
- type CrossEntropy
- type Differentiable
- type Dump
- type Layer
- type Linear
- type Loss
- type LossType
- type MeanSquared
- type Mode
- type Neural
- func (n *Neural) ApplyWeights(weights [][][]float64)
- func (n Neural) Dump() *Dump
- func (n *Neural) Forward(input []float64) error
- func (n Neural) Marshal() ([]byte, error)
- func (n *Neural) NumWeights() (num int)
- func (n *Neural) Predict(input []float64) []float64
- func (n *Neural) String() string
- func (n Neural) Weights() [][][]float64
- type Neuron
- type ReLU
- type Sigmoid
- type Synapse
- type Tanh
- type WeightInitializer
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
Types ¶
type ActivationType ¶
type ActivationType int
ActivationType is represents a neuron activation function
const ( // ActivationNone is no activation ActivationNone ActivationType = iota // ActivationSigmoid is a sigmoid activation ActivationSigmoid // ActivationTanh is hyperbolic activation ActivationTanh // ActivationReLU is rectified linear unit activation ActivationReLU // ActivationLinear is linear activation ActivationLinear // ActivationSoftmax is a softmax activation (per layer) ActivationSoftmax )
func OutputActivation ¶
func OutputActivation(c Mode) ActivationType
OutputActivation returns activation corresponding to prediction mode
type BinaryCrossEntropy ¶
type BinaryCrossEntropy struct{}
BinaryCrossEntropy is binary CE loss
func (BinaryCrossEntropy) Df ¶
func (l BinaryCrossEntropy) Df(estimate, ideal, activation float64) float64
Df is CE'(...)
func (BinaryCrossEntropy) F ¶
func (l BinaryCrossEntropy) F(estimate, ideal [][]float64) float64
F is CE(...)
type Config ¶
type Config struct {
// Number of inputs
Inputs int
// Defines topology:
// For instance, [5 3 3] signifies a network with two hidden layers
// containing 5 and 3 nodes respectively, followed an output layer
// containing 3 nodes.
Layout []int
// Activation functions: {ActivationTanh, ActivationReLU, ActivationSigmoid}
Activation ActivationType
// Solver modes: {ModeRegression, ModeBinary, ModeMultiClass, ModeMultiLabel}
Mode Mode
// Initializer for weights: {NewNormal(σ, μ), NewUniform(σ, μ)}
Weight WeightInitializer `json:"-"`
// Loss functions: {LossCrossEntropy, LossBinaryCrossEntropy, LossMeanSquared}
Loss LossType
// Apply bias nodes
Bias bool
}
Config defines the network topology, activations, losses etc
type CrossEntropy ¶
type CrossEntropy struct{}
CrossEntropy is CE loss
func (CrossEntropy) Df ¶
func (l CrossEntropy) Df(estimate, ideal, activation float64) float64
Df is CE'(...)
type Differentiable ¶
Differentiable is an activation function and its first order derivative, where the latter is expressed as a function of the former for efficiency
func GetActivation ¶
func GetActivation(act ActivationType) Differentiable
GetActivation returns the concrete activation given an ActivationType
type Layer ¶
type Layer struct {
Neurons []*Neuron
A ActivationType
}
Layer is a set of neurons and corresponding activation
func NewLayer ¶
func NewLayer(n int, activation ActivationType) *Layer
func (*Layer) ApplyBias ¶
func (l *Layer) ApplyBias(weight WeightInitializer) []*Synapse
ApplyBias creates and returns a bias synapse for each neuron in l
func (*Layer) Connect ¶
func (l *Layer) Connect(next *Layer, weight WeightInitializer)
Connect fully connects layer l to next, and initializes each synapse with the given weight function
type Loss ¶
type Loss interface {
F(estimate, ideal [][]float64) float64
Df(estimate, ideal, activation float64) float64
}
Loss is satisfied by loss functions
type MeanSquared ¶
type MeanSquared struct{}
MeanSquared in MSE loss
func (MeanSquared) Df ¶
func (l MeanSquared) Df(estimate, ideal, activation float64) float64
Df is CE'(...)
type Mode ¶
type Mode int
Mode denotes interference mode
const ( // ModeDefault is unspecified mode ModeDefault Mode = iota // ModeMultiClass is for one-hot encoded classification, applies softmax output layer ModeMultiClass // ModeRegression is regression, applies linear output layer ModeRegression // ModeBinary is binary classification, applies sigmoid output layer ModeBinary // ModeMultiLabel is for multilabel classification, applies sigmoid output layer ModeMultiLabel )
type Neural ¶
Neural is a neural network
func (*Neural) ApplyWeights ¶
ApplyWeights sets the weights from a three-dimensional slice
func (*Neural) NumWeights ¶
NumWeights returns the number of weights in the network
type Neuron ¶
type Neuron struct {
A ActivationType `json:"-"`
In []*Synapse
Out []*Synapse
Value float64 `json:"-"`
}
Neuron is a neural network node
func NewNeuron ¶
func NewNeuron(activation ActivationType) *Neuron
type Synapse ¶
Synapse is an edge between neurons
func NewSynapse ¶
NewSynapse returns a synapse with the specified initialized weight
type WeightInitializer ¶
type WeightInitializer func() float64
A WeightInitializer returns a (random) weight
func NewNormal ¶
func NewNormal(stdDev, mean float64) WeightInitializer
NewNormal returns a normal weight generator
func NewUniform ¶
func NewUniform(stdDev, mean float64) WeightInitializer
NewUniform returns a uniform weight generator
Source Files
¶
Directories
¶
| Path | Synopsis |
|---|---|
|
Package luaml is the require()-able host module that exposes the ml neural- network engine (native/ml + native/ml/training) to LuaScript as `ml`.
|
Package luaml is the require()-able host module that exposes the ml neural- network engine (native/ml + native/ml/training) to LuaScript as `ml`. |