WOLFRAM

Wolfram Language & System Documentation Center
Wolfram Language Home Page »

"Boolean" (Net Decoder)

[Experimental]

NetDecoder["Boolean"]

represents a decoder that converts a probability p to False if p<0.5, and True otherwise.

Details

  • NetDecoder[…][input] applies the decoder to an input to produce an output.
  • NetDecoder[…][{input1,input2,…}] applies the decoder to a list of inputs to produce a list of outputs.
  • The input to the decoder input is a scalar in the range 0≤input≤1.
  • NetDecoder[{"Boolean","InputDepth"->n}] can be used to specify that the input array has depth n. The default depth is 0, indicating that the input is a single real number.
  • A decoder can be attached to an output port of a net by specifying "port"->NetDecoder[…] when constructing the net.
    • Properties
  • NetDecoder["Boolean"][data,prop] can be used to calculate a specific property for the input data.
  • When a "Boolean" decoder is attached to a net, net[data,prop] or net[data,"oport"->prop] can be used to calculate a specific property of the decoded output.
  • The "Boolean" decoder supports the following properties prop:
  • "Decision"the Boolean class False or True with the highest probability (default)
    "Probability"the probability p of class True
    "Entropy"the entropy of the probability distribution
    "RandomSample"sample a Boolean proportionally to its probability
    "RandomSample"->tsample using a positive temperature t
    Nonebypass decoding and return the input

Examples

open allclose all

Basic Examples  (1)Summary of the most common use cases

Create a Boolean decoder:

In[1]:=1
✖
https://wolfram.com/xid/0nrs25q30lp6bm7xqkihhyq-gfwb36
Out[1]=1

Decode a probability as either True or False:

In[2]:=2
✖
https://wolfram.com/xid/0nrs25q30lp6bm7xqkihhyq-q05whz
Out[2]=2

The decoder maps over a batch of examples:

In[3]:=3
✖
https://wolfram.com/xid/0nrs25q30lp6bm7xqkihhyq-fi4lo8
Out[3]=3

The decoder expects probabilities as inputs and acts as Identity with the property "Probability":

In[4]:=4
✖
https://wolfram.com/xid/0nrs25q30lp6bm7xqkihhyq-80d8u
Out[4]=4

Compute the entropy:

In[5]:=5
✖
https://wolfram.com/xid/0nrs25q30lp6bm7xqkihhyq-j5yqv6
Out[5]=5

Scope  (2)Survey of the scope of standard use cases

Attach a "Boolean" decoder to the output port of an ElementwiseLayer:

In[1]:=1
✖
https://wolfram.com/xid/0nrs25q30lp6bm7xqkihhyq-i5qidn
Out[1]=1

Apply the layer to an input:

In[2]:=2
✖
https://wolfram.com/xid/0nrs25q30lp6bm7xqkihhyq-w0vpfh
Out[2]=2

Create a "Boolean" decoder that converts a matrix of probabilities into a matrix of Boolean values:

In[1]:=1
✖
https://wolfram.com/xid/0nrs25q30lp6bm7xqkihhyq-y14pic
Out[1]=1

Attach the decoder to a net and apply it to an input:

In[2]:=2
✖
https://wolfram.com/xid/0nrs25q30lp6bm7xqkihhyq-m4sj7j
Out[2]=2
In[3]:=3
✖
https://wolfram.com/xid/0nrs25q30lp6bm7xqkihhyq-hoxqlm
Out[3]=3

Obtain the probability of the positive class:

In[4]:=4
✖
https://wolfram.com/xid/0nrs25q30lp6bm7xqkihhyq-fj8t2q
Out[4]=4

Compute the entropy of each Bernoulli distribution:

In[5]:=5
✖
https://wolfram.com/xid/0nrs25q30lp6bm7xqkihhyq-9b7dda
Out[5]=5