Hi there, heres my problem, on an orthogonal system, where a vehicle can only go up, down, left or right, lets assign each one of those possibilities to an output nerve, and setup a NNet to connect to those outputs. Some Inputs --> NN --> 4 Outputs Now, when a certain output is fired, the vechicle will go in that direction... My problem is, how do i make the NN only fire ONE of the outputs? What system is commonly used for mutually-exclusive decisions, when one of the decisions cant be taken at the same time as others? Thanx for any tips on this...

---

[Hugo Ferreira][Positronic Dreams][Colibri 3D Engine][Entropy HL2 MOD][Yann L.][Enginuity]
The most irrefutable evidence that there is intelligent life in the Universe is that they haven''t contacted us!

The obvious thing to do is selecting the output with the highest value. There are ANN architectures where the neurons in the last layer inhibit each other, but I don''t have any experience with that.

Output with the highest value?

In my designs, outputs only take the form of 0 or 1, fire or not fire, so there isnt really a "higher" value i can take.

Neurons that inhibit each other? this is interesting, can you provide any links to this?

Thanks.

---

[Hugo Ferreira][Positronic Dreams][Colibri 3D Engine][Entropy HL2 MOD][Yann L.][Enginuity]
The most irrefutable evidence that there is intelligent life in the Universe is that they haven''t contacted us!

quote:

---

Original post by pentium3id
Neurons that inhibit each other? this is interesting, can you provide any links to this?

---

A connection between two artificial neurons is inhibitary if the connection weight is negative. In other words, if the parent neuron fires, its affect is to decrease the likelihood of the child neuron firing, thus the ''inhibitory'' label.

Timkin

quote:

---

Original post by pentium3id
Output with the highest value?

In my designs, outputs only take the form of 0 or 1, fire or not fire, so there isnt really a "higher" value i can take.

---

Well, you''re going to have to do one of 3 things:

1. Give up the binary outputs for graded ones, which allows selection of the strongest.

2. Force the neural network to generate a single ''1'' output (lateral inhibition is one option).

3. Choose an output arbitrarily.

-Predictor
http://will.dwinnell.com

take the random value with equal probailities for "1"s

I''d model the problem differently, ruling out mutually exclusive options by design. Use turn left/right, move forward/back.

Alex

---

AiGameDev.com

I''d agree with Alex on this one... why do you feel that an ANN is an appropriate tool for this decision task? What is it about the domain that precludes the many other reliable and less semantically challenged solution methods.

Timkin

What do you mean when you write "semantically challenged "?

-Predictor
http://will.dwinnell.com

Timkin, because the work im doing is about a new NN design.
The neurons themselves are diferent both in implementation and mathematicly, and the way the NN evolves is also a bit unorthodox.

The Left/Right aproach, in which a NN allways takes a decision, even it doesnt fire, although the best solution for the current problem, isnt correct (imho) purely from a design standpoint.

A NN shouldnt be forced into making a decision every single time, and thats my point.

In nature, how are "conflicts of opinion" solved?

---

[Hugo Ferreira][Positronic Dreams][Colibri 3D Engine][Entropy HL2 MOD][Yann L.][Enginuity]
The most irrefutable evidence that there is intelligent life in the Universe is that they haven''t contacted us!