Gamestudio Links
Zorro Links
Newest Posts
Instrument Price Zorro Chart
by felixfx. 10/19/19 20:48
Today real live account blown - my experience
by Clifford_B. 10/19/19 17:09
Building Diversified Portfolios - New Paper
by SnoopySniff. 10/18/19 16:23
Indices & metals easier to trade than FX???
by SnoopySniff. 10/18/19 10:08
What are you working on?
by txesmi. 10/17/19 07:00
Ducascopy exporter
by line7. 10/17/19 06:21
AUM Magazine
Latest Screens
The Space Between
Pogostuck: Rage With Your Friends
Worst Case Z
AckCon'18 - Lotter vs the World 2 - Preview Release
Who's Online Now
3 registered members (Dooley, AndrewAMD, Seymour), 736 guests, and 4 spiders.
Key: Admin, Global Mod, Mod
Newest Members
VillageTalkies, line7, Shutch, Clifford_B, Paulius
18310 Registered Users
Previous Thread
Next Thread
Print Thread
Rate Thread
Deep learning framework for regression #477845
08/03/19 14:00
08/03/19 14:00
Joined: Dec 2014
Posts: 135
Germany
sdh309795gaas Offline OP
Member
sdh309795gaas  Offline OP
Member

Joined: Dec 2014
Posts: 135
Germany
I really want to try my luck with regression instead of simple classification with deep learning. Unfortunately, there isn't any example code available.

The zorro developers gave these frameworks (strategy folder):

DeepLearn.r
DeepLearnH2O.r
DeepLearnKeras.r
DeepLearnMX.r

They are all set up for classification. What would I need to change to use these for regression? I'm especially interested in MXnet.

Re: Deep learning framework for regression [Re: sdh309795gaas] #477857
08/05/19 15:11
08/05/19 15:11
Joined: Jan 2019
Posts: 71
berlin
L
laz Offline
Junior Member
laz  Offline
Junior Member
L

Joined: Jan 2019
Posts: 71
berlin
In DeepLearn.r you can find the following:
Code
neural.train = function(model,XY) 
{
  XY <- as.matrix(XY)
  X <- XY[,-ncol(XY)]
  Y <- XY[,ncol(XY)]
  Y <- ifelse(Y > 0,1,0)
  Models[[model]] <<- sae.dnn.train(X,Y,
      hidden = c(10,30,10), 
      activationfun = "tanh", 
      learningrate = 0.5, 
      momentum = 0.5, 
      learningrate_scale = 1.0, 
      output = "sigm", 
      sae_output = "linear", 
      numepochs = 100, 
      batchsize = 100,
      hidden_dropout = 0, 
      visible_dropout = 0)
}

Start from here, Y <- ifelse(Y > 0,1,0) changes the target from trade returns to a 0/1 signal, you need to remove that...

Check sae.dnn.train, how can one do regression with it, test every step with a minimal example and data you know well...

for example - do sae.dnn.train regression on iris data wink

Find a metric, RMSE, MAE, Rsquared, read about them - use them - or write your own...

It is possible but it is a long way, i have done all that but i have connected the caret framework to zorro. Now i can do do both,

classification or regression with all caret models.

Re: Deep learning framework for regression [Re: laz] #477973
08/20/19 11:28
08/20/19 11:28
Joined: Dec 2014
Posts: 135
Germany
sdh309795gaas Offline OP
Member
sdh309795gaas  Offline OP
Member

Joined: Dec 2014
Posts: 135
Germany
Thank you, I will check this out!


Gamestudio download | chip programmers | Zorro platform | shop | Data Protection Policy

oP group Germany GmbH | Birkenstr. 25-27 | 63549 Ronneburg / Germany | info (at) opgroup.de

Powered by UBB.threads™ PHP Forum Software 7.7.1