MeanAbsoluteLossLayer

✖
`MeanAbsoluteLossLayer`

[Experimental]

✖

represents a loss layer that computes the mean absolute loss between the "Input" port and "Target" port.

Details and Options

MeanAbsoluteLossLayer exposes the following ports for use in NetGraph etc.:
"Input" an array of arbitrary rank

"Target" an array of the same rank as "Input"

"Loss" a real number
MeanAbsoluteLossLayer[…][<|"Input" -> in, "Target"target|>] explicitly computes the output from applying the layer.
MeanAbsoluteLossLayer[…][<|"Input"->{in₁,in₂,…},"Target"->{target₁,target₂,…}|>] explicitly computes outputs for each of the in_i and target_i.
When given a NumericArray as input, the output will be a NumericArray.
MeanAbsoluteLossLayer is typically used inside NetGraph to construct a training network.
A MeanAbsoluteLossLayer[…] can be provided as the third argument to NetTrain when training a specific network.
MeanAbsoluteLossLayer["port"->shape] allows the shape of the given input "port" to be specified. Possible forms for shape include:

	"Real"	a single real number
	n	a vector of length n
	{n₁,n₂,…}	an array of dimensions n₁×n₂×…
	"Varying"	a vector whose length is variable
	{"Varying",n₂,n₃,…}	an array whose first dimension is variable and whose remaining dimensions are n₂×n₃×…
	NetEncoder[…]	an encoder
	NetEncoder[{…,"Dimensions"{n₁,…}}]	an encoder mapped over an array of dimensions n₁×…

Options[MeanAbsoluteLossLayer] gives the list of default options to construct the layer. Options[MeanAbsoluteLossLayer[…]] gives the list of default options to evaluate the layer on some data.
Information[MeanAbsoluteLossLayer[…]] gives a report about the layer.
Information[MeanAbsoluteLossLayer[…],prop] gives the value of the property prop of MeanAbsoluteLossLayer[…]. Possible properties are the same as for NetGraph.

Examples

open allclose all

Basic Examples (3)Summary of the most common use cases

Create a MeanAbsoluteLossLayer layer:

In[1]:=1

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-9reqx3

Out[1]=1

Create a MeanAbsoluteLossLayer that takes length-3 vectors:

In[1]:=1

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-cfiivd

Out[1]=1

Apply the layer to data:

In[2]:=2

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-0n9a3o

Out[2]=2

Create a NetGraph containing a MeanAbsoluteLossLayer:

In[1]:=1

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-39v8wd

Out[1]=1

Apply the net to input data:

In[2]:=2

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-3g473h

Out[2]=2

Scope (4)Survey of the scope of standard use cases

Arguments (1)

Create a MeanAbsoluteLossLayer:

In[1]:=1

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-437fy3

Out[1]=1

Apply the MeanAbsoluteLossLayer to a pair of matrices:

In[2]:=2

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-xfv3o2

Out[2]=2

Apply the MeanAbsoluteLossLayer to a pair of vectors:

In[3]:=3

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-hxlt7u

Out[3]=3

Apply the MeanAbsoluteLossLayer to a pair of numbers:

In[4]:=4

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-ytsn5g

Out[4]=4

Ports (3)

Create a MeanAbsoluteLossLayer that assumes the input data are vectors of length 2:

In[1]:=1

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-rowe7w

Out[1]=1

Thread the layer across a batch of inputs:

In[2]:=2

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-fojtxu

Out[2]=2

Create a MeanAbsoluteLossLayer that takes two variable-length vectors:

In[1]:=1

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-1w1d3n

Out[1]=1

Apply the layer to an input and target vector:

In[2]:=2

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-x3ytxw

Out[2]=2

Thread the layer over a batch of input and target vectors:

In[3]:=3

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-uu191j

Out[3]=3

Create a MeanAbsoluteLossLayer that takes two images as input:

In[1]:=1

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-bq1zo4

Out[1]=1

Apply the layer to two dissimilar images:

In[2]:=2

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-us5jzd

Out[2]=2

Apply the layer to two dissimilar images:

In[3]:=3

✖

https://wolfram.com/xid/0yj2be51zi33znaduq-wx7xun

Out[3]=3

Applications (1)Sample problems that can be solved with this function

Define a single-layer neural network that takes in scalar numeric values and produces scalar numeric values, and train this network using a MeanAbsoluteLossLayer:

In[1]:=1