Looking for a good problem for a solution I have coded :)

  • Thread starter Thread starter tomekd789
  • Start date Start date
AI Thread Summary
Tomasz has developed an abstraction for breeding neural networks using a genetic algorithm and is seeking practical problems to apply it to. Initial attempts included number factorization, 3-SAT satisfiability, and Forex trading, yielding mixed results. A suggestion was made to predict human-generated coin toss sequences, where the neural network achieved 70% accuracy with a minimal architecture. Further inquiries focused on the network's performance compared to simple predictive strategies and its capabilities in solving linear systems or learning tasks. Suggestions for potential problems included exploring genetic algorithms for decryption tasks, starting with simple codes like the Caesar cipher, and considering challenges involving linear systems, which can be complex and tedious to solve manually.
tomekd789
Messages
3
Reaction score
1
I have coded the following abstraction for breeding neural networks with a genetic algorithm: https://github.com/tomekd789/clogann
Now I am looking for a problem to solve using it. It would be ideal if it is non trivial, of practical significance, and matching the tool. So far I've tried:
  • Numbers factorization (with a mediocre effect)
  • Checking satisfiability of random 3-SAT terms taken from the phase transition area (http://www.princeton...s/gent94sat.pdf) (somehow dissatisfied; did not reach the goal of proving P = NP http://cdn01.codecall.net/public/style_emoticons/default/wink.png )
  • Forex (with positive effects, but not worth the effort).
All hints welcome.

Regards,
Tomasz
 
Last edited by a moderator:
Technology news on Phys.org
Solution looking for a problem is often not cost-effective.
 
Anything more concrete? ;)
Meanwhile, I've been advised to take a sequence of "coin tosses" generated manually by a human (i.e. no real coins, no computer involved, just from one's head) and breed a network capable of predicting next tosses results. I was astonished: for 1000 "coin tosses" the network was 70% correct.
I.e. we humans are quite predictable, at least in this case. :)
Another surprise was the necessary minimal size of the network: just two input neurons, and three extra, one treated as output, too.

Still looking for other ideas.
Tomasz
 
Which ratio do you get if you simply predict "the opposite of the previous coin"? Is the neural net better than that?
 
65.2%, then still slightly worse.
 
  • Like
Likes mfb
At first glimpse this isn't very significant. What does your algorithm? Can it solve linear systems or can it learn?
Without being an expert I'd try to google 'genetic algebras' and see what kind of problems there are.
Or try some decryption problems. You can start with an easy Cesar code. Just to see how it performs. And then more difficult ones.
(I'd have a bunch of tasks but they all involve solving linear systems with free variables. They are ##O(n^3)## which quickly makes it boring to solve them by hand.)
 
Dear Peeps I have posted a few questions about programing on this sectio of the PF forum. I want to ask you veterans how you folks learn program in assembly and about computer architecture for the x86 family. In addition to finish learning C, I am also reading the book From bits to Gates to C and Beyond. In the book, it uses the mini LC3 assembly language. I also have books on assembly programming and computer architecture. The few famous ones i have are Computer Organization and...
What percentage of programmers have learned to touch type? Have you? Do you think it's important, not just for programming, but for more-than-casual computer users generally? ChatGPT didn't have much on it ("Research indicates that less than 20% of people can touch type fluently, with many relying on the hunt-and-peck method for typing ."). 'Hunt-and-peck method' made me smile. It added, "For programmers, touch typing is a valuable skill that can enhance speed, accuracy, and focus. While...
I had a Microsoft Technical interview this past Friday, the question I was asked was this : How do you find the middle value for a dataset that is too big to fit in RAM? I was not able to figure this out during the interview, but I have been look in this all weekend and I read something online that said it can be done at O(N) using something called the counting sort histogram algorithm ( I did not learn that in my advanced data structures and algorithms class). I have watched some youtube...

Similar threads

Back
Top