Abs returns a new operator node as a result of the `Abs` function.

Add returns a new operator node as a result of the gradfn.Add function.

AddScalar returns a new operator node as a result of the gradfn.AddScalar function.

Affine returns a new operator node as a result of the gradfn.Affine function.

AppendRows returns a new operator node as a result of the gradfn.AppendRows function.

At returns a new operator node as a result of the gradfn.At function.

Backward initiates back-propagation from the input tensors.

BiAffine performs a biaffine transformation.

BiLinear performs a bilinear transformation of the type (x_1 W x_2).

CELU returns a new operator node as a result of the gradfn.CELU function.

ColView returns a new operator node as a result of the gradfn.ColView function.

ColViews calls ColView for each column of x, returning a new slice of column-view Nodes.

Concat returns a new operator node as a result of the gradfn.Concat function.

Copy returns a new operator node as a result of the gradfn.Copy function.

Cos returns a new operator node as a result of the `Cos` function.

Div returns a new operator node as a result of the gradfn.Div function.

DivScalar returns a new operator node as a result of the gradfn.DivScalar function.

Dot returns a new operator node as a result of the gradfn.Dot function.

Dropout returns a new operator node as a result of the gradfn.Dropout function.

DropoutFunc returns a function to create a Dropout operator working with the given dropout probability.

ELU returns a new operator node as a result of the gradfn.ELU function.

Exp returns a new operator node as a result of the `Exp` function.

Flatten returns a new operator node as a result of the gradfn.Flatten function.

GELU returns a new operator node as a result of the gradfn.GELU function.

HardSigmoid returns a new operator node as a result of the `HardSigmoid` function.

HardTanh returns a new operator node as a result of the `HardTanh` function.

LeakyReLU returns a new operator node as a result of the gradfn.LeakyReLU function.

Log returns a new operator node as a result of the `Log` function.

LogSoftmax returns a new operator node as a result of Log(Softmax(x)).

LogSumExp "trick" computes the log of the sum of exponentials of input elements.

ManualSeed sets the seed for generating random numbers.

Map returns a transformed version of xs with all its components modified according to the mapping function.

Map2 takes two arguments and applies a mapping function (that must take two arguments) to the items from the two node-slices in parallel.

Max returns a new operator node as a result of the gradfn.Max function.

Maximum returns the value that describes the maximum of the sample.

MaxPooling returns a new operator node as a result of the gradfn.MaxPooling function.

Mean returns the value that describes the average of the sample.

Min returns a new operator node as a result of the gradfn.Min function.

Minimum returns the value that describes the minimum of the sample.

Mish returns a new operator node as a result of the `Mish` function.

Mul returns a new operator node as a result of the gradfn.Mul function.

Neg returns a new operator node as a result of the `Neg` function.

NewOperator creates a new operator with the given AutoGradFunction.

Pad down/up samples the input to the given size.

PositiveELU returns a new operator node as a result of ELU(x) + 1.

Pow returns a new operator node as a result of the gradfn.Pow function.

Prod returns a new operator node as a result of the gradfn.Prod function.

ProdScalar returns a new operator node as a result of the gradfn.ProdScalar function.

Rand returns the global random number generator.

Reciprocal returns a new operator node as a result of the `Reciprocal` function.

ReduceMax returns a new operator node as a result of the gradfn.ReduceMax function.

ReduceMean returns a new operator node as a result of the gradfn.ReduceMean function.

ReduceSum returns a new operator node as a result of the gradfn.ReduceSum function.

ReLU returns a new operator node as a result of the `ReLU` function.

Reshape returns a new operator node as a result of the gradfn.Reshape function.

ReverseSub returns a new operator node as a result of the fn.ReverseSub function.

ReverseSubOne returns a new operator node as a result of applying reverse subtraction with 1.0 to the input using the fn.ReverseSub function.

RotateR performs the right circular shift.

RowView returns a new operator node as a result of the gradfn.RowView function.

RowViews calls RowView for each row of x, returning a new slice of row-view Nodes.

ScalarMax returns a new operator node as a result of the gradfn.ScalarMax function.

Seed sets the seed for generating random numbers to the current time (converted to uint64).

SELU returns a new operator node as a result of the gradfn.SELU function.

SeparateMatrix returns a matrix of Node(s) represented as a slice of slice containing the elements extracted from the input.

SeparateVec returns a slice of Node(s) containing the elements extracted from the input.

SetForceSyncExecution enables or disables the forcing of synchronous execution for all operators.

Sigmoid returns a new operator node as a result of the `Sigmoid` function.

SiLU returns a new operator node as a result of the fn.SiLU function.

Sin returns a new operator node as a result of the `Sin` function.

Slice returns a new operator node as a result of the gradfn.Slice function.

Softmax returns a new operator node as a result of the gradfn.Softmax function.

SoftPlus returns a new operator node as a result of the gradfn.SoftPlus function.

SoftShrink returns a new operator node as a result of the gradfn.SoftShrink function.

Softsign returns a new operator node as a result of the `SoftSign` function.

SparseMax returns a new operator node as a result of the gradfn.SparseMax function.

SparseMaxLoss returns a new operator node as a result of the gradfn.SparseMaxLoss function.

SplitVec splits the x Node into multiple chunks.

Sqrt returns a new operator node as a result of the `Sqrt` function.

Square returns a new operator node as a result of the gradfn.Prod(x, x) function.

Stack returns a new operator node as a result of the gradfn.Stack function.

StopGrad creates a new GradientBlocker that stops the accumulated gradients from flowing through the wrapped Node.

Sub returns a new operator node as a result of the gradfn.Sub function.

SubScalar returns a new operator node as a result of the gradfn.SubScalar function.

Sum returns the value that describes the sum of the sample.

Swish returns a new operator node as a result of the gradfn.Swish function.

SwishB returns a new operator node as a result of the gradfn.SwishB function.

T returns a new operator node as a result of the fn.T function.

Tan returns a new operator node as a result of the `Tan` function.

Tanh returns a new operator node as a result of the `Tanh` function.

Threshold returns a new operator node as a result of the gradfn.Threshold function.

GradientBlocker embeds any tensors implementation disabling gradients handling and blocking gradients accumulation.

Operator is a type of node.

AutoGradFunction represents a function with automatic differentiation features.