axis=list(integer) or integer

name=string

The ReduceAll(t,opts) command computes the logical And of elements across a Tensor.

The ReduceAny(t,opts) command computes the logical Or of elements across a Tensor.

The ReduceJoin(t,opts) command concatenates string elements across a Tensor.

The ReduceLogSumExp(t,opts) command computes the logical logsumexp of elements across a Tensor. (This operation first exponentiates each entry being computed, adds the results, then takes the logarithm of the sum.)

The ReduceMax(t,opts) command computes the maximum of elements across a Tensor.

The ReduceMean(t,opts) command computes the mean of elements across a Tensor.

The ReduceMin(t,opts) command computes the minimum of elements across a Tensor.

The ReduceProduct(t,opts) command computes the product of elements across a Tensor.

The ReduceSum(t,opts) command computes the sum of elements across a Tensor.

$\mathrm{with}\left(\mathrm{DeepLearning}\right)\:$

$W≔\mathrm{Constant}\left(\left[0.3\,0.7\right]\,\mathrm{datatype}=\mathrm{float}\left[8\right]\right)$

$W≔\left[\begin{array}{c}\mathrm{DeepLearning\; Tensor}\\ \mathrm{Shape:\; [2]}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

$b≔\mathrm{Constant}\left(\left[-0.3\,0.2\right]\,\mathrm{datatype}=\mathrm{float}\left[8\right]\right)$

$b≔\left[\begin{array}{c}\mathrm{DeepLearning\; Tensor}\\ \mathrm{Shape:\; [2]}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

$x≔\mathrm{Variable}\left(\left[0.2\,0.4\right]\,\mathrm{datatype}=\mathrm{float}\left[8\right]\right)$

$x≔\left[\begin{array}{c}\mathrm{DeepLearning\; Variable}\\ \mathrm{Name:\; Variable:0}\\ \mathrm{Shape:\; [2]}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

$\mathrm{linear\_model}≔Wx+b$

$\mathrm{linear\_model}≔\left[\begin{array}{c}\mathrm{DeepLearning\; Tensor}\\ \mathrm{Shape:\; [2]}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

$y≔\mathrm{Variable}\left(\left[1.0\,0.\right]\,\mathrm{datatype}=\mathrm{float}\left[8\right]\right)$

$y≔\left[\begin{array}{c}\mathrm{DeepLearning\; Variable}\\ \mathrm{Name:\; Variable:0}\\ \mathrm{Shape:\; [2]}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

$\mathrm{loss}≔\mathrm{ReduceSum}\left({\left(\mathrm{linear\_model}-y\right)}^2\right)$

$\mathrm{loss}≔\left[\begin{array}{c}\mathrm{DeepLearning\; Tensor}\\ \mathrm{Shape:\; []}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

The DeepLearning/Tensor/ReduceAll, DeepLearning/Tensor/ReduceAny, DeepLearning/Tensor/ReduceJoin, DeepLearning/Tensor/ReduceLogSumExp, DeepLearning/Tensor/ReduceMax, DeepLearning/Tensor/ReduceMean, DeepLearning/Tensor/ReduceMin, DeepLearning/Tensor/ReduceProduct and DeepLearning/Tensor/ReduceSum commands were introduced in Maple 2018.

For more information on Maple 2018 changes, see Updates in Maple 2018.