Modifier and Type | Interface and Description |
---|---|
interface |
Accumulation
An accumulation is an op that given:
x -> the origin ndarray
y -> the pairwise ndarray
n -> the number of times to accumulate
Of note here in the extra arguments.
|
interface |
ScalarOp |
interface |
TransformOp
Transform operation:
stores the result in an ndarray
|
Modifier and Type | Class and Description |
---|---|
class |
BaseAccumulation
Base class for accumulation, initiates the initial entry
with respect to the child class.
|
class |
BaseOp
Base op.
|
class |
BaseScalarOp
Base scalar operation
|
class |
BaseTransformOp
A base op for basic getters and setters
|
Modifier and Type | Method and Description |
---|---|
Op |
Op.opForDimension(int index,
int dimension)
A copy of this operation for a particular dimension of the input
|
Modifier and Type | Method and Description |
---|---|
Op |
OpExecutioner.exec(Op op)
Execute the operation
|
Op |
DefaultOpExecutioner.exec(Op op) |
Op |
OpExecutioner.exec(Op op,
int dimension)
Execute the operation
|
Op |
DefaultOpExecutioner.exec(Op op,
int dimension) |
Modifier and Type | Method and Description |
---|---|
Op |
OpExecutioner.exec(Op op)
Execute the operation
|
Op |
DefaultOpExecutioner.exec(Op op) |
Op |
OpExecutioner.exec(Op op,
int dimension)
Execute the operation
|
Op |
DefaultOpExecutioner.exec(Op op,
int dimension) |
void |
OpExecutioner.iterateOverAllColumns(Op op)
Iterate over every column of every slice
|
void |
DefaultOpExecutioner.iterateOverAllColumns(Op op) |
void |
OpExecutioner.iterateOverAllRows(Op op)
Iterate over every row of every slice
|
void |
DefaultOpExecutioner.iterateOverAllRows(Op op) |
Modifier and Type | Class and Description |
---|---|
class |
Bias
Calculate a bias
|
class |
Dot
Dot product
|
class |
IAMax
Calculate the max over a vector
|
class |
Max
Calculate the max over a vector
|
class |
Mean
Calculate the mean of the vector
|
class |
Min
Calculate the min over a vector
|
class |
Norm1
Sum of absolute values
|
class |
Norm2
Sum of absolute values
|
class |
NormMax
The max absolute value
|
class |
Prod
Prod the components
|
class |
StandardDeviation
Standard deviation (sqrt of variance)
|
class |
Sum
Sum the components
|
class |
Variance
Variance with bias correction.
|
Modifier and Type | Method and Description |
---|---|
Op |
Min.opForDimension(int index,
int dimension) |
Op |
IAMax.opForDimension(int index,
int dimension) |
Op |
Norm2.opForDimension(int index,
int dimension) |
Op |
Max.opForDimension(int index,
int dimension) |
Op |
Bias.opForDimension(int index,
int dimension) |
Op |
NormMax.opForDimension(int index,
int dimension) |
Op |
Sum.opForDimension(int index,
int dimension) |
Op |
Norm1.opForDimension(int index,
int dimension) |
Op |
Variance.opForDimension(int index,
int dimension) |
Op |
Prod.opForDimension(int index,
int dimension) |
Op |
StandardDeviation.opForDimension(int index,
int dimension) |
Op |
Mean.opForDimension(int index,
int dimension) |
Op |
Dot.opForDimension(int index,
int dimension) |
Modifier and Type | Class and Description |
---|---|
class |
CosineSimilarity
Cosine similarity
Note that you need to initialize
a scaling constant equal to the norm2 of the
vector
|
class |
EuclideanDistance
Euclidean distance
|
class |
ManhattanDistance
Manhattan distance
|
Modifier and Type | Method and Description |
---|---|
Op |
CosineSimilarity.opForDimension(int index,
int dimension) |
Op |
ManhattanDistance.opForDimension(int index,
int dimension) |
Op |
EuclideanDistance.opForDimension(int index,
int dimension) |
Modifier and Type | Class and Description |
---|---|
class |
ScalarAdd
Scalar addition
|
class |
ScalarDivision
Scalar division
|
class |
ScalarMax
Scalar max operation.
|
class |
ScalarMultiplication
Scalar multiplication
|
class |
ScalarReverseDivision
Scalar reverse division
|
class |
ScalarReverseSubtraction
Scalar reverse subtraction
|
class |
ScalarSubtraction
Scalar subtraction
|
Modifier and Type | Method and Description |
---|---|
Op |
ScalarReverseDivision.opForDimension(int index,
int dimension) |
Op |
ScalarSubtraction.opForDimension(int index,
int dimension) |
Op |
ScalarAdd.opForDimension(int index,
int dimension) |
Op |
ScalarMultiplication.opForDimension(int index,
int dimension) |
Op |
ScalarReverseSubtraction.opForDimension(int index,
int dimension) |
Op |
ScalarDivision.opForDimension(int index,
int dimension) |
Op |
ScalarMax.opForDimension(int index,
int dimension) |
Modifier and Type | Class and Description |
---|---|
class |
ScalarEquals
Return a binary (0 or 1) when greater than a number
|
class |
ScalarGreaterThan
Return a binary (0 or 1) when greater than a number
|
class |
ScalarGreaterThanOrEqual
Return a binary (0 or 1) when greater than or equal to a number
|
class |
ScalarLessThan
Return a binary (0 or 1) when less than a number
|
class |
ScalarLessThanOrEqual
Return a binary (0 or 1) when less than
or equal to a number
|
class |
ScalarNotEquals
Return a binary (0 or 1) when greater than a number
|
class |
ScalarSetValue
Scalar value set operation.
|
Modifier and Type | Method and Description |
---|---|
Op |
ScalarGreaterThanOrEqual.opForDimension(int index,
int dimension) |
Op |
ScalarEquals.opForDimension(int index,
int dimension) |
Op |
ScalarLessThan.opForDimension(int index,
int dimension) |
Op |
ScalarGreaterThan.opForDimension(int index,
int dimension) |
Op |
ScalarLessThanOrEqual.opForDimension(int index,
int dimension) |
Op |
ScalarSetValue.opForDimension(int index,
int dimension) |
Op |
ScalarNotEquals.opForDimension(int index,
int dimension) |
Modifier and Type | Class and Description |
---|---|
class |
Abs
Abs elementwise function
|
class |
ACos
Log elementwise function
|
class |
ASin
Arcsin elementwise function
|
class |
ATan
Arc Tangent elementwise function
|
class |
Ceil
Ceiling elementwise function
|
class |
Cos
Cosine elementwise function
|
class |
Exp
Exp elementwise function
|
class |
Floor
Floor elementwise function
|
class |
HardTanh
Hard tanh elementwise function
|
class |
HardTanhDerivative
Hard tanh elementwise function
|
class |
Identity
Identity function
|
class |
Log
Log elementwise function
|
class |
MaxOut
Max out activation:
http://arxiv.org/pdf/1302.4389.pdf
|
class |
Negative
Negative function
|
class |
OneMinus
1 - input
|
class |
Ones
Ones (represents a constant)
|
class |
Pow
Pow function
|
class |
RectifedLinear
Rectified linear units
|
class |
Round
Rounding function
|
class |
SetRange
Set range to a particular set of values
|
class |
Sigmoid
Sigmoid function
|
class |
SigmoidDerivative
Sigmoid derivative
|
class |
Sign
Signum function
|
class |
Sin
Log elementwise function
|
class |
SoftMax
Soft max function
row_maxes is a row vector (max for each row)
row_maxes = rowmaxes(input)
diff = exp(input - max) / diff.rowSums()
Outputs a probability distribution.
|
class |
SoftMaxDerivative
Softmax derivative
|
class |
Sqrt
Sqrt funciton
|
class |
Stabilize
Stabilization function, forces values to be within a range
|
class |
Tanh
Tanh elementwise function
|
class |
VectorFFT
Encapsulated vector operation
|
class |
VectorIFFT
Single ifft operation
|
Modifier and Type | Method and Description |
---|---|
Op |
Abs.opForDimension(int index,
int dimension) |
Op |
VectorFFT.opForDimension(int index,
int dimension) |
Op |
Sqrt.opForDimension(int index,
int dimension) |
Op |
Ceil.opForDimension(int index,
int dimension) |
Op |
Negative.opForDimension(int index,
int dimension) |
Op |
Sigmoid.opForDimension(int index,
int dimension) |
Op |
ASin.opForDimension(int index,
int dimension) |
Op |
Tanh.opForDimension(int index,
int dimension) |
Op |
Stabilize.opForDimension(int index,
int dimension) |
Op |
RectifedLinear.opForDimension(int index,
int dimension) |
Op |
Identity.opForDimension(int index,
int dimension) |
Op |
HardTanhDerivative.opForDimension(int index,
int dimension) |
Op |
Ones.opForDimension(int index,
int dimension) |
Op |
Exp.opForDimension(int index,
int dimension) |
Op |
MaxOut.opForDimension(int index,
int dimension) |
Op |
OneMinus.opForDimension(int index,
int dimension) |
Op |
Round.opForDimension(int index,
int dimension) |
Op |
SoftMaxDerivative.opForDimension(int index,
int dimension) |
Op |
SetRange.opForDimension(int index,
int dimension) |
Op |
SigmoidDerivative.opForDimension(int index,
int dimension) |
Op |
Floor.opForDimension(int index,
int dimension) |
Op |
ACos.opForDimension(int index,
int dimension) |
Op |
ATan.opForDimension(int index,
int dimension) |
Op |
Sin.opForDimension(int index,
int dimension) |
Op |
Pow.opForDimension(int index,
int dimension) |
Op |
Cos.opForDimension(int index,
int dimension) |
Op |
VectorIFFT.opForDimension(int index,
int dimension) |
Op |
HardTanh.opForDimension(int index,
int dimension) |
Op |
Log.opForDimension(int index,
int dimension) |
Op |
Sign.opForDimension(int index,
int dimension) |
Op |
SoftMax.opForDimension(int index,
int dimension) |
Modifier and Type | Class and Description |
---|---|
class |
AddOp
Addition operation
|
class |
CopyOp
Copy operation
|
class |
DivOp
Division operation
|
class |
MulOp
Multiplication operation
|
class |
SubOp
Subtraction operation
|
Modifier and Type | Method and Description |
---|---|
Op |
CopyOp.opForDimension(int index,
int dimension) |
Op |
SubOp.opForDimension(int index,
int dimension) |
Op |
AddOp.opForDimension(int index,
int dimension) |
Op |
DivOp.opForDimension(int index,
int dimension) |
Op |
MulOp.opForDimension(int index,
int dimension) |
Modifier and Type | Class and Description |
---|---|
class |
Eps
Bit mask over the ndarrays as to whether
the components are equal or not
|
class |
EqualTo
Bit mask over the ndarrays as to whether
the components are equal or not
|
class |
GreaterThan
Bit mask over the ndarrays as to whether
the components are greater than or not
|
class |
GreaterThanOrEqual
Bit mask over the ndarrays as to whether
the components are greater than or equal or not
|
class |
LessThan
Bit mask over the ndarrays as to whether
the components are less than or not
|
class |
LessThanOrEqual
Bit mask over the ndarrays as to whether
the components are less than or equal or not
|
class |
NotEqualTo
Not equal to function:
Bit mask over whether 2 elements are not equal or not
|
Modifier and Type | Method and Description |
---|---|
Op |
LessThan.opForDimension(int index,
int dimension) |
Op |
Min.opForDimension(int index,
int dimension) |
Op |
LessThanOrEqual.opForDimension(int index,
int dimension) |
Op |
EqualTo.opForDimension(int index,
int dimension) |
Op |
GreaterThan.opForDimension(int index,
int dimension) |
Op |
Max.opForDimension(int index,
int dimension) |
Op |
NotEqualTo.opForDimension(int index,
int dimension) |
Op |
Eps.opForDimension(int index,
int dimension) |
Op |
GreaterThanOrEqual.opForDimension(int index,
int dimension) |
Modifier and Type | Class and Description |
---|---|
class |
TestAccumulation
Created by agibsonccc on 2/22/15.
|
class |
TestOp
Test operation
|
Modifier and Type | Method and Description |
---|---|
Op |
TestOp.opForDimension(int index,
int dimension) |
Op |
TestAccumulation.opForDimension(int index,
int dimension) |
Copyright © 2015. All Rights Reserved.