WOLFRAM

Wolfram Language & System Documentation Center
Wolfram Language Home Page »

"NeuralNetwork" (Machine Learning Method)

[Experimental]
  • Method for Classify and Predict.
  • Models class probabilities or predicts the value distribution using a neural network.

Details & Suboptions

  • A neural network consists of stacked layers, each performing a simple computation. Information is processed layer by layer from the input layer to the output layer. The neural network is trained to minimize a loss function on the training set using gradient descent.
  • The following options can be given:
  • MaxTrainingRounds Automaticmaximum number of iterations over the dataset
    "NetworkDepth" Automaticthe depth of the network
  • The option "NetworkDepth" controls the capacity of the network. A deeper network will be able to fit more complex patterns but will be more prone to overfitting.
  • The option MaxTrainingRounds can be used to speed up the training but also as a regularization parameter: setting a lower value can prevent overfitting.

Examples

open allclose all

Basic Examples  (2)Summary of the most common use cases

Train a classifier function on labeled examples:

In[1]:=1
✖
https://wolfram.com/xid/0cbeghptcwbmi3e-iexj8n
Out[1]=1

Obtain information about the classifier:

In[2]:=2
✖
https://wolfram.com/xid/0cbeghptcwbmi3e-bzw8uc
Out[2]=2

Classify a new example:

In[3]:=3
✖
https://wolfram.com/xid/0cbeghptcwbmi3e-g4ebwa
Out[3]=3

Generate some data and visualize it:

In[1]:=1
✖
https://wolfram.com/xid/0cbeghptcwbmi3e-ef76x2
Out[1]=1

Train a predictor function on it:

In[2]:=2
✖
https://wolfram.com/xid/0cbeghptcwbmi3e-fj7crm
Out[2]=2

Compare the data with the predicted values and look at the standard deviation:

In[3]:=3
✖
https://wolfram.com/xid/0cbeghptcwbmi3e-bcq515
Out[3]=3

Options  (2)Common values & functionality for each option

MaxTrainingRounds  (1)

Generate a training set and visualize it:

In[1]:=1
✖
https://wolfram.com/xid/0cbeghptcwbmi3e-rz6f9f
Out[1]=1

Train two predictors using different MaxTrainingRounds and compare their performances on the training set:

In[2]:=2
✖
https://wolfram.com/xid/0cbeghptcwbmi3e-mz0by0
In[3]:=3
✖
https://wolfram.com/xid/0cbeghptcwbmi3e-6mqt1k
Out[3]=3

"NetworkDepth"  (1)

Use the "NetworkDepth" suboption to specify the number of units in the neural network:

In[1]:=1
✖
https://wolfram.com/xid/0cbeghptcwbmi3e-tl156l
Out[1]=1

Train a second PredictorFunction by changing the "NetworkDepth":

In[2]:=2
✖
https://wolfram.com/xid/0cbeghptcwbmi3e-xzyqce
Out[2]=2

Plot the mean prediction:

In[3]:=3
✖
https://wolfram.com/xid/0cbeghptcwbmi3e-yjyd8a
Out[3]=3