# backpropagation per interacting object idea

This topic is 1481 days old which is more than the 365 day threshold we allow for new replies. Please post a new topic.

## Recommended Posts

ok, if you manage to pull objects apart of your 3d depth eye. (which cant be that hard alot of the time)

any identified object, can have a backpropagation of its relative values of its sorrounding environment, to its movement.

that way you can now 'pretend' your other things.

then you can randomize a calculus transform of relative variables to the environment again to the motor outputs of the creature...  and if you can pretend what the other things do, you can simulate as fast as you want and develop a real physical solution to the problem its having with other moving objects.

you can supply more and more power, to the randomizer, i dont know how good random can develop successful behaviour... depends on how you score it definitely.

##### Share on other sites

Yes.. combine it with interpolation of the possibility matrix, you may have a solid system.

##### Share on other sites

ive just drawn up my maths parts, and im just about to go detect a function.  ill come back with my preliminary results.  im not sure about anything.

heres my 12 parts, am i missing anything?

//conditional
#define PART_CLAMP      0    //this is my deactivation switch, required for multistate in a single numerical pipe.

//exponents and bases
#define PART_POWER      1    //2 inputs
#define PART_EXP        2    //2 inputs   - this is discovering the exponent of a given base.
#define PART_BASE       3    //2 inputs  - this is discovering the base of a given exponent.

//4 preschool arithmetic
#define PART_SCALE      4
#define PART_BIAS       5
#define PART_POLARITY   6    //swap pole.
#define PART_INVERT     7    //swap division bar.

//4 specialist vector scalars   (direct x  opengl stuff)
#define PART_DOT        8
#define PART_CROSS      9
#define PART_NORMALIZE  10
#define PART_MAGNITUDE  11
Edited by rouncer

##### Share on other sites

How did detection go?

1. 1
Rutin
25
2. 2
3. 3
4. 4
JoeJ
18
5. 5

• 14
• 14
• 11
• 11
• 9
• ### Forum Statistics

• Total Topics
631759
• Total Posts
3002138
×