About
I am a Mathematics and Computer Science undergrad at the Université de Provence in Marseille, France. My interests range from abstract math to concrete computer science, and even science in general.
Alp Mestanogullari's Blog
Pages
Recent posts
- My blog has moved
- scoutess, continuous integration, cabal and the Google Summer of Code
- A French community for Haskell
- Getting GHC HEAD and LLVM working together
- HNN news
Recent Comments
Top Posts
Tags
Archives
- December 2013 (1)
- March 2012 (1)
- October 2011 (1)
- March 2010 (1)
- February 2010 (2)
- January 2010 (1)
- December 2009 (3)
- November 2009 (1)
- October 2009 (4)
- September 2009 (2)
Blogs I follow
- Alain Defrance's Blog
- Brent Yorgey's blog
- Dan Piponi's (sigfpe) blog
- Don Stewart's blog
- Grégoire Duchêne's blog
- Jawher's blog
- Maxime Roger Cyr's blog
- metagoto's C++ blog
- Roman Kecher's blog
- Schum's blog
- The Comonad.Reader
My twitter
- @christopherdone Thanks again. I'll make sure to remind people that when they use it. Good evening! 15 hours ago
- @christopherdone Oh neat, thanks a lot! Do you control the lpaste bot too? To make it join the channel to announce the pastes there. 15 hours ago
- @christopherdone btw, lpaste is being flooded a bit: lpaste.net/browse 18 hours ago
- @christopherdone hey. what do I have to do to get a channel added to lpaste? would like to add #servant -- for haskell-servant.github.io 18 hours ago
- @conal Good luck in your search! I'm sure you'll find something fun. I wish I/we had the funds to hire you =) 19 hours ago
Hi Alp,
is there possible to build neural network with multiple layers in HNN? From its sources it seams, that it can have only two tiers:
check :: [[Neuron]] -> Bool
check nss = let l = length nss in l > 1 && l [[Neuron]]
nn nss | check nss = nss
| otherwise = error “Invalid nn”
Why it can’t take here any number of layers?
best regards,
Robert
Robert,
I just wrote this first version when I was learning Haskell and so I went for simplicity and since theoretically we’re guaranteed that it’s enough, I just stopped there. However, we’re preparing (for a long time now) a new version. But let me warn you that I’m quite busy, so is the other guy working on HNN so we’re a bit short on time and don’t know at all when it’ll be available. So let me know if you’re interested!