FromDense fills dst (mat.Mutable) with src (mat.Dense).

MatDenseColSlice returns a *mat.Dense view of partial underlaying data of M.

MatDenseRowSlice returns a *mat.Dense view of partial underlaying data of M.

MatDenseSlice returns a *mat.Dense view of partial underlaying data of M.

MatDimsCheck checks compat of operator op and its Matrix parameters Dims.

MatDimsString returns a string representing Dims of its several Matrix parameters.

MatGeneralColSlice returns a blas64.General view of partial underlaying data of M.

MatGeneralRowSlice returns a blas64.General view of partial underlaying data of M.

MatGeneralSlice returns a blas64.General view of partial underlaying data of M.

MatStr return a string from a mat.Matrix.

NewAdadeltaOptimizer return a *SGDOptimizer setup for adadelta.

NewAdagradOptimizer return a *SGDOptimizer setup for adagrad.

NewAdamOptimizer returns an initialized adam solver.

NewLockedSource returns a rand.Source safe for concurrent access.

NewOptimizer only accepts SGD|adagrad|adadelta|rmsprop|adam.

NewRMSPropOptimizer return a *SGDOptimizer setup for rmsprop.

NewSGDOptimizer returns an initialized *SGDOptimizer with stepsize 1e-4 and momentum 0.9.

NewSolver returns an OptimCreator.

NewSource returns a new pseudo-random Source seeded with the given value.

Parallelize split execution over NSamples across threads.

ToDense returns w view of m if m is a RawMatrixer, et returns a dense copy of m.

Activations is the map of implemented activation functions.

GOMethodCreators is the map of all gonum optimize method creators (gonum native method creators + base.Optimizer creators).

Solvers is the map for common Optimizer creators agd,adagrad,rmsprop,adadelta,adam.

Identity ...

LockedSource is an implementation of Source that is concurrency-safe.

Logistic ...

MatConst is a matrix where all cless have the same value.

MatOnesPrepended is a matrix override representing its initializer with an initial column of ones added.

MatRowSlice is a matrix row chunk.

MatTranspose is a matrix override to transpose a mat.Matrix from its initializer.

ReLU ...

SGDOptimizer is struct for SGD solver v https://en.wikipedia.org/wiki/Stochastic_gradient_descent.

Tanh ...

Activation is the inteface for an activation function.

Fiter have a Fit(Matrix,Matrix) Fitter method.

Float64er is implemented by a random source having a method Float64() float64.

Intner is implemented by a random source having a method Intn() float64.

NormFloat64er is implemented by a random source having a method NormFloat64() float64.

Optimizer has updateParams method to update theta from gradient.

Permer is implemented by a random source having a method Perm(int) []int.

Predicter have Predict(Matrix,Mutable).

Shuffler is implemented by a random source having a method Shuffle(int,func(int,int)).

SourceCloner is an "golang.org/x/exp/rand".Source with a Clone method.

Transformer transforms X,Y into Xout,Yout.

GOMethodCreator is a func that creates a gonum/optimize.Method.

OptimCreator is the type for functions returning an Optimizer.

RandomState represents a bit more than random_state pythonic attribute.

Sigmoid ...

A Source represents a source of uniformly-distributed pseudo-random int64 values in the range [0, 1<<64).