_convertToOneOfMany in PyBrain

Question

I follow the PyBrain tutorial Classification with Feed-Forward Neural Networks and want to build my own classifier.

I do not understand how _convertToOneOfMany modifies outputs.

Why would initial operation alldata.addSample(input, [klass]) create more than one output neuron per class?

@user425720 Even if you answered yourself, you should mark it as answered. Then people know that this solved the problem for you. — Martin Thoma, May 31 '16 at 04:16

score 6 · Accepted Answer · answered Nov 29 '11 at 13:25

6

nevermind, here is doc explaining this stuff http://pybrain.org/docs/tutorial/datasets.html

answered Nov 29 '11 at 13:25

user425720

3,578
1
21
23

1

thanks for this answer, but I don't quite follow the doc "many algorithms work better if classes are encoded into one output unit per class". may I ask what is "one output unit per class"? – hihell Oct 16 '14 at 16:53
wow, it was years ago, I can hardly remember - Isn't it connected to neural network structure? So, a neuron can emit output to one or many neurons in another layer? – user425720 Oct 17 '14 at 08:43
yes it is related to NT structure. actually I figured out myself, "one output unit per class" means if you have 3 classed, it'd be better if you also have 3 output units. and _convertToOneOfMany does this for you by expand/shrink output units to the number of your target classes – hihell Oct 18 '14 at 12:37

JunWangCas · Answer 2 · 2014-07-06T06:53:24.170

2

Target number is [0,1,2], this function translate them to (001,010,100). This is because many algorithms work better if classes are encoded into one output unit per class

edited Jul 06 '14 at 06:53

answered Jul 06 '14 at 06:28

JunWangCas

89
1
7

Martin Thoma · Answer 3 · 2016-05-31T04:09:36.590

The relevant part in the docs is the page Using Datasets: classification – Datasets for Supervised Classification Training:

When doing classification, many algorithms work better if classes are encoded into one output unit per class, that takes on a certain value if the class is present. As an advanced feature, ClassificationDataSet does this conversion automatically:

However, this is not an satisfying answer as I don't understand either why there should be more than one output neuron per class in the first hand.

Update: I recommend using keras

_convertToOneOfMany in PyBrain

3 Answers3

Linked