# Package org.nd4j.linalg.api.ops.impl.accum

• Class Summary
Class Description
All
Boolean AND accumulation
AMax
Calculate the absolute max over a vector
AMean
Calculate the absolute mean of the given vector
AMin
Calculate the absolute minimum over a vector
Any
Boolean AND pairwise transform
ArgMax
ASum
Absolute sum the components
BaseReduction
BatchMmul
Batched matrix multiplication.
Bias
Calculate a bias
CountNonZero
Count the number of non-zero elements
CountZero
Count the number of zero elements
CumProd
CumSum
Cumulative sum operation, optionally along dimension.
Dot
Dot product
Entropy
Entropy Op - returns the entropy (information gain, or uncertainty of a random variable).
EqualsWithEps
Operation for fast INDArrays equality checks
LogEntropy
Log Entropy Op - returns the log entropy (information gain, or uncertainty of a random variable).
LogSumExp
LogSumExp - this op returns https://en.wikipedia.org/wiki/LogSumExp
MatchCondition
This operation returns number of elements matching specified condition
Max
Calculate the max over an array
Mean
Calculate the mean of the vector
Min
Calculate the min over an array
Mmul
Matrix multiplication/dot product
Moments
Norm1
Sum of absolute values
Norm2
Sum of squared values (real) Sum of squared complex modulus (complex)
NormalizeMoments
NormMax
The max absolute value
Prod
Prod the components
ShannonEntropy
Non-normalized Shannon Entropy Op - returns the entropy (information gain, or uncertainty of a random variable).
SigmoidCrossEntropyLoss
Sigmoid cross entropy loss with logits
SoftmaxCrossEntropyLoss
Softmax cross entropy loss
SoftmaxCrossEntropyLossWithLogits
Softmax cross entropy loss with Logits
SquaredNorm
Squared norm (sum_i x_i^2) reduction operation
StandardDeviation
Standard deviation (sqrt of variance)
Sum
Sum the components
TensorMmul
TensorMmul
Variance
Variance with bias correction.
WeightedCrossEntropyLoss
Weighted cross entropy loss with logits
ZeroFraction
Compute the fraction of zero elements