On Fri, Aug 21, 2009 at 13:37, Frank Berger
<address@hidden> wrote:
What I am denoting is that the NNP "learns" the attributes of the
specific roll generator you use. And does it probably better than a
human can.
Why? quite easy. Any NN I'm aware of is presented the position to evaluate it.
Therefore it never sees the dice and can therefore not learn a pattern.
A state space convolutioon CAN and DOES learn attributions from a aseries of rolls:
otherwise the network would not learn, whether held static AFTER learning or not.
This is so close to 1st grade I wonder if people wil see it immediately.
This is interesting. The Mersenne Twister is linear, so in principle it
is "easy" to learn how to predict it. Whether a neural net will in fact
learn how to predict it depends on a lot of things, but it's entirely
believable.
The Mersenne Twister isn't cryptographic strength but fulfills quite some statistical tests.
AFAIK as long as you don't need cryptogrphic strengt MT is regarded as the best choice.
Therefore to train a neural net to predict something that is nearly undistinguish from real random
is an absolute waste of time. Even with a simple linear congruence random number generator
it's a waste of time.
When youy train the NN< it is trained. Whether your training INTENDS to train it in that way does not change whether or not all or a portion of that training is in fact DOEN by the training you select for another purpose.
So your arguemnt is again specious.
No. It wouldn't be interesting and no it wouldn't show any effect.
Even if a RNG was heavily biased throwin e.g. 25% 3's and even if the NN would see the dice the effect would even out over the large number of different positions presented the net during learning. And even if there was an effect on the 8th post point digit it would be completely overridden by the effect of the initial randomization of the NN
Noo, it owuld NOT even out; any experience Backgammon player will tell you that.
For example, removing ALL threes from the rolls WIL produce a DIFERENT game
Similarly, removing 99.99%, 899.9% or 90%.
ANY bias wil change the flow of the game. ANY game.
Analyzing the effect of rng on NN seems to me as useful as analyzing conspiracy theory...
Ad hominems. Not math, and not nackgamoon, fer sure.
.