WOLFRAM

Wolfram Language & System Documentation Center

SequenceLastLayer[]

represents a net that takes a sequence of inputs and returns the last element of the sequence.

Details and Options
Details and Options Details and Options
Examples  
Basic Examples  
Scope  
Ports  
Applications  
Possible Issues  
See Also
Tech Notes
Related Guides
History
Cite this Page

SequenceLastLayer

SequenceLastLayer[]

represents a net that takes a sequence of inputs and returns the last element of the sequence.

Details and Options

  • SequenceLastLayer[] represents a net that takes a sequence of arrays and outputs a single array.
  • SequenceLastLayer[…][input] explicitly computes the output from applying the layer.
  • SequenceLastLayer[…][{input1,input2,…}] explicitly computes an output for each of the inputi.
  • When given a NumericArray as input, the output will be a NumericArray.
  • SequenceLastLayer is typically used inside NetChain, NetGraph, etc.
  • The input and output ports of the net represented by SequenceLastLayer[] are:
  • "Input"a sequence of rank-n arrays
    "Output"a rank-n array
  • SequenceLastLayer["Input"->shape] allows the shape of the input to be specified. Possible forms for shape are:
  • na sequence of n numbers
    "Varying"a vector whose length is variable
    {len,d1,d2,…}sequence of len arrays of dimensions d1×d2×…
    {"Varying",d1,d2,…}varying number of arrays of dimensions d1×d2×…
  • Options[SequenceLastLayer] gives the list of default options to construct the layer. Options[SequenceLastLayer[…]] gives the list of default options to evaluate the layer on some data.
  • Information[SequenceLastLayer[…]] gives a report about the layer.
  • Information[SequenceLastLayer[…],prop] gives the value of the property prop of SequenceLastLayer[…]. Possible properties are the same as for NetGraph.

Examples

open all close all

Basic Examples  (2)

Create a SequenceLastLayer:

Wolfram Language code: SequenceLastLayer[]

Create a SequenceLastLayer that expects a sequence of vectors of size 3:

Wolfram Language code: last = SequenceLastLayer["Input" -> {"Varying", 3}]

Apply the layer to a sequence:

Wolfram Language code: last[{{1, 2, 3}, {4, 5, 6}, {7, 8, 9}}]

Scope  (2)

Ports  (2)

Create a SequenceLastLayer that expects a length-3 sequence of 2×2 matrices:

Wolfram Language code: last = SequenceLastLayer["Input" -> {3, 2, 2}]

Apply the layer to a sequence:

Wolfram Language code: last[{{{1, 2}, {4, 5}}, {{7, 8}, {10, 11}}, {{12, 13}, {14, 15}}}]

Create a SequenceLastLayer that expects a sequence of real numbers:

Wolfram Language code: last = SequenceLastLayer["Input" -> "Varying"]

Apply the layer to an input:

Wolfram Language code: last[{1, 2, 3}]

The layer threads across a batch of inputs:

Wolfram Language code: last[{{1, 2, 3}, {4, 5}, {6, 7, 8, 9}}]

Applications  (1)

SequenceLastLayer is commonly used to obtain a fixed-sized representation of a sequence, needed for tasks such as sequence classification, by taking the final output from a recurrent layer:

Wolfram Language code: classify = NetChain[{BasicRecurrentLayer[10], SequenceLastLayer[], LinearLayer[3], SoftmaxLayer[]}, "Input" -> {"Varying", 3}, "Output" -> NetDecoder[{"Class", {"a", "b", "c"}}]]

Possible Issues  (1)

SequenceLastLayer cannot accept symbolic inputs:

Wolfram Language code: last = SequenceLastLayer[]; last[{1, 2}]
Wolfram Language code: last[{1, z}]
Wolfram Research (2017), SequenceLastLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/SequenceLastLayer.html.

Text

Wolfram Research (2017), SequenceLastLayer, Wolfram Language function, https://reference.wolfram.com/language/ref/SequenceLastLayer.html.

CMS

Wolfram Language. 2017. "SequenceLastLayer." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/SequenceLastLayer.html.

APA

Wolfram Language. (2017). SequenceLastLayer. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/SequenceLastLayer.html

BibTeX

@misc{reference.wolfram_2026_sequencelastlayer, author="Wolfram Research", title="{SequenceLastLayer}", year="2017", howpublished="\url{https://reference.wolfram.com/language/ref/SequenceLastLayer.html}", note=[Accessed: 13-June-2026]}

BibLaTeX

@online{reference.wolfram_2026_sequencelastlayer, organization={Wolfram Research}, title={SequenceLastLayer}, year={2017}, url={https://reference.wolfram.com/language/ref/SequenceLastLayer.html}, note=[Accessed: 13-June-2026]}