-1

I have 3 neurons x1, x2, x3. Now I know my value is being overflowed by the actual result value at output (as it is wrong answer) and my weights need new value, but how much value to be set for each neuron ? How to calculate that ?

One way is to divide the (desired value - output value) / 3 and assign the answer to each neuron ... but it won't work for new input, as no proper learning is made.

matthias_h
  • 11,356
  • 9
  • 22
  • 40
overuser
  • 21
  • 1
  • 3
  • 1
    Can you elaborate more? Are x1 x2 x3 output nodes or the whole network? What do you mean when you say a value is being overflowed? – A--- Sep 19 '14 at 23:44
  • x1 x2 x3 are the hidden layer after inputs and my whole network consists only these 3 neurons , now value overflow means that the output answer is .5 higer then the actual value according to the inputs – overuser Sep 20 '14 at 14:09
  • what type of neural network are you trying to build and how do you calculate the neurons weights? I doubt that anybody can actually answer your question without any more specific information on what you are trying to do. – Sim Sep 20 '14 at 23:37
  • Possible duplicate of [Clarification on a Neural Net that plays Snake](http://stackoverflow.com/questions/42099814/clarification-on-a-neural-net-that-plays-snake) – devinbost Feb 15 '17 at 20:37

1 Answers1

1

From your question it seems you do not understand yet how really neural networks work.

First of all, neural networks are a class of algorithms that fall under machine learning techniques. Therefore, they learn, either unsupervised, supervised or in a reinforcement type of training. This of course require a learning paradigm. In neural networks the most well studied supervised training is the backpropagation method. However, to understand how this work you first need to understand how a network is developed.

A description of what is a neural network and its foundations can be seen here: http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html

One practical explanation how you can implement a functional network through backpropagation can be seen here: http://galaxy.agh.edu.pl/~vlsi/AI/backp_t_en/backprop.html

If you read these you will probably know enough to answer your question.

ASantosRibeiro
  • 1,247
  • 8
  • 15