Re: Can we neural networks to predict code change?
- From: Stephen Harris <cyberguard-1048@xxxxxxxxx>
- Date: Sat, 30 Dec 2006 18:56:22 GMT
Chris Smith wrote:
<joshipura@xxxxxxxxx> wrote:I have never studied theoretical computer science. However, I know a
few facts:
2. Neural networks are not digital computers - and can solve somethings
Turing machine can not
If you mean a form of neural networks that can be implemented on any ordinary computer, then you are wrong; neural networks can't do anything that's not possible with a Turing machine. If nothing else, a Turing machine could at least simulate the neural network performing the computation.
If you are referring to biological neural networks -- e.g., human brains -- and asserting that they are capable of things that couldn't be simulated by a computer at all, then this is philosophy rather than computer science.
My question:
Is it theoretically possible to
A. Train a neural network about past and current code in form of change
in graph and
B. Ask it to predict what the next change could be?
Our brain predicts which module might fail next while maintaining a
large code base - with reasonable accuracy. Why can't it be done
through neural networks?
As was already said, there are certainly going to be reasonable heuristics, and artificial neural networks (and therefore Turing machines) may be able to pick up on them and pick them out of a body of past experience and application of logic. I would conjecture that this is essentially what the human brain does, as well. However, it's clear that neither the human brain nor any kind of computer can give an exact answer in the general case.
Artificial neural networks and human neural networks are physically
different (analog). Your opinion that the ANN could likely approximate some of the functions of the human brain seems uncontroversial. However using the word "essentially" is close to adopting the Computationalist
thesis (top-down) or the (bottom-up) ANN approach or a hybrid of the two. Essentially, implies all of the functions, which is philosophical.
To paraphrase Turing, a Turing Machine can do any task that a human clerk can do who uses paper, pencil, eraser and a "by rote" procedure.
Computers do this, so certainly some functions are approximated, but
there is quite a gap in equating Turing's description to the essential
process of the human brain generalized into its functionality.
One can teach a dog to fetch a paper, but not to read it. One can
assemble a program to do expert medical diagnosis, but all attempts to bundle many expert program into a complete package fail for lack of an organizing principle.
The brain has an organizing principle, survival, which serves to filter
our logical decisions through instincts, which are not even listable.
So the human neural network and ANNs are not essentially the same. I
suppose this is also a philosophical assumption but is does not suffer
from 50 years of circumstantial evidence: failure, as essentially does.
Regards,
Stephen
.
- References:
- Can we neural networks to predict code change?
- From: joshipura
- Re: Can we neural networks to predict code change?
- From: Chris Smith
- Can we neural networks to predict code change?
- Prev by Date: Re: Can we neural networks to predict code change?
- Next by Date: Re: Can we neural networks to predict code change?
- Previous by thread: Re: Can we neural networks to predict code change?
- Next by thread: passive radar theory refrence needed
- Index(es):
Relevant Pages
|
