3rd generation NN, deep learning, deep belief nets and Restricted Boltzmann Machines

This is a discussion on 3rd generation NN, deep learning, deep belief nets and Restricted Boltzmann Machines within the Trading Software forums, part of the Commercial category; The purpouse of this thread would be to verify if the deep belief nets trained for Restricted Boltzmann Machines can ...

Reply
 
LinkBack Thread Tools Search this Thread
Old Oct 15, 2010, 3:04pm   #1
Joined Jan 2009
3rd generation NN, deep learning, deep belief nets and Restricted Boltzmann Machines

The purpouse of this thread would be to verify if the deep belief nets trained for Restricted Boltzmann Machines can predict or classify FOREX strategies results. The comparative analysis with results obtained using Support Vector Machines with different kernels can be also done.

Deep belief nets seems to be quite new thing based on analysis of human brain way to work. Links to video tutorials are below

http://videolectures.net/icml09_bengio_lecun_tldar/
http://videolectures.net/mlss09uk_hinton_dbn/
http://videolectures.net/jul09_hinton_deeplearn/

The most research seems to be done by Mr. Hinton from Uni of Toronto and Mr Yann and Mr. Taylor from Uni of NY see links

http://www.cs.toronto.edu/~hinton/
http://www.cs.toronto.edu/~hinton/Ma...encePaper.html

http://www.cs.nyu.edu/~gwtaylor/
http://www.cs.nyu.edu/~yann/

To achieve our goals we can use already existing FOREX system TradeFX which is using MATLAB + MT4 and using Support Vector Machines for classification

http://www.columbia.edu/~xv2103/fina...deFX/index.htm
http://www.columbia.edu/~xv2103/fina...eFX/Report.htm


For people interested in SVM theory here is very good video course

http://videolectures.net/epsrcws08_campbell_isvm/

So our tasks would be:


1) double check if all scripts of TradeFX are correct (already bugs found in three of them) and eventually expand this design by adding e.g. Buy Orders

2) Adapt the MATLAB code of Hintons autoencoder to be usable with TradeFX

3) Adapt the MATLAB code related to Phd Thesis of Taylor to be usable with TradeFX

4) Try to change standard MATLAB SVM kernel to different one (e.g. Wavelet)

Than back test and OOS test for systems from 2,3,4 can be done and results compared.

All code is dowloadable from links above

Questions are welcome

Krzysztof

Last edited by Krzysiaczek99; Oct 16, 2010 at 1:29am.
Krzysiaczek99 is offline   Reply With Quote
Thanks! The following members like this post: khyangg
Old Oct 15, 2010, 3:53pm   #2
Joined Jan 2007
Re: 3rd generation NN, deep learning, deep belief nets and Restricted Boltzmann Machi

Hi Krzysztof,
Thanks for starting this thread. Hope we get some help from members.
fralo is offline   Reply With Quote
Old Oct 15, 2010, 6:06pm   #3
Joined Jan 2007
Re: 3rd generation NN, deep learning, deep belief nets and Restricted Boltzmann Machi

You suggested a video lecture by Benjio to learn autoencoders. http://videolectures.net/icml09_bengio_lecun_tldar/

I followed that to Benjio site, and eventually to here:

http://www.deeplearning.net/software/theano/

Apparantly the software used by Benjio group. It is Python based, but has transparent use of GPU's for speed. Beyond my ken, but may be useful to some other visitor.
fralo is offline   Reply With Quote
Old Oct 15, 2010, 7:06pm   #4
 
Pat494's Avatar
Joined Mar 2004
Re: 3rd generation NN, deep learning, deep belief nets and Restricted Boltzmann Machi

From someone who has tried the usual neural nets and found they didn't seem very good, I would be interested to know if these new nets give better results ?
__________________
Pensioners unite for equal pensions.
After the "rat race " is run
let's have a decent country for all to live in.
You too will be a pensioner one day.
If you live long enough.

Pat494 is offline   Reply With Quote
Old Oct 16, 2010, 1:13am   #5
Joined Jan 2009
Re: 3rd generation NN, deep learning, deep belief nets and Restricted Boltzmann Machi

Quote:
Originally Posted by Pat494 View Post
From someone who has tried the usual neural nets and found they didn't seem very good, I would be interested to know if these new nets give better results ?
Indeed...that is the question:
Whether 'tis nobler in the mind to suffer
The slings and arrows of outrageous fortune,
Or to take arms against a sea of troubles
...etc (thanks, Bard)

This a very thought provoking (yes, computer, pun intended), and somewhat intimidating exercise. A little too late to do anything today, so

To sleep: perchance to dream

and then, maybe tomorrow, we will think on

The undiscover'd country from whose bourn
No traveller returns, puzzles...


Dude, this poetry is a rush, you can read anything you like into it
Dommo is offline   Reply With Quote
Old Oct 16, 2010, 1:18am   #6
Joined Jan 2009
Re: 3rd generation NN, deep learning, deep belief nets and Restricted Boltzmann Machi

In all seriousness, thanks to Krzysiaczek for this very thought provoking post. I dread to think what you are like at chess.
Dommo is offline   Reply With Quote
Old Oct 16, 2010, 1:20am   #7
Joined Nov 2008
Re: 3rd generation NN, deep learning, deep belief nets and Restricted Boltzmann Machi

Listened to the first few minutes of one of these out of curiosity..and I have to say it sounds like a pile of sh1t..... deliberately vague and pseudo -complicated ..maybe it gets better further on in...anyone else have more patience ?
Prawnsandwich is offline   Reply With Quote
Old Oct 16, 2010, 1:25am   #8
Joined Jan 2009
Re: 3rd generation NN, deep learning, deep belief nets and Restricted Boltzmann Machi

Quote:
Originally Posted by Prawnsandwich View Post
Listened to the first few minutes of one of these out of curiosity..and I have to say it sounds like a pile of sh1t..... deliberately vague and pseudo -complicated ..maybe it gets better further on in...anyone else have more patience ?
Oddly, that is a very precise description of my response to technical analysis.
Dommo is offline   Reply With Quote
Reply

Thread Tools Search this Thread
Search this Thread:

Advanced Search

Similar Threads
Thread Thread Starter Forum Replies Last Post
Neural Networks - Genetic Algorithms - Boltzmann Machines - FOREX crystal balls? gtatix Forex 27 Apr 30, 2012 9:27am
How deep is your Level II? insight2 Technical Analysis 6 Apr 29, 2008 10:41pm
In at the deep end! superspur First Steps 12 Dec 24, 2007 11:34am
Deep insight Disqplay Trading Software 1 Feb 7, 2006 12:01am
Deep INsight NKE Trading Software 0 Apr 8, 2005 10:57am

LinkBacks (?)
LinkBack to this Thread: http://www.trade2win.com/boards/trading-software/105880-3rd-generation-nn-deep-learning-deep-belief-nets-restricted-boltzmann-machines.html
Posted By For Type Date
Better NN EA development - Page 82 - Forex-TSD This thread Pingback Oct 17, 2010 12:51pm

Currently Active Users Viewing This Thread: 1 (0 members and 1 guests)