Comments on: Deep Learning Systems for Bitcoin 1 https://financial-hacker.com/deep-learning-systems-for-bitcoins-part-1/ A new view on algorithmic trading Wed, 21 Jun 2023 07:24:58 +0000 hourly 1 By: jcl https://financial-hacker.com/deep-learning-systems-for-bitcoins-part-1/#comment-92307 Wed, 21 Jun 2023 07:24:58 +0000 http://www.financial-hacker.com/?p=2899#comment-92307 Since I had not found the time for doing the second part in the last 2 years, I must admit that the statistical probability is slim that I will in the next 2 years.

]]> By: Paul Jones https://financial-hacker.com/deep-learning-systems-for-bitcoins-part-1/#comment-92306 Wed, 21 Jun 2023 06:13:03 +0000 http://www.financial-hacker.com/?p=2899#comment-92306 The Deep Learning “time-series prediction” field is moving fast. Any word when https://financial-hacker.com/deep-learning-systems-for-bitcoins-part-2/ will become reality? Or is it indefinitely on hold?

]]> By: jcl https://financial-hacker.com/deep-learning-systems-for-bitcoins-part-1/#comment-69386 Wed, 27 Jan 2021 10:04:40 +0000 http://www.financial-hacker.com/?p=2899#comment-69386 The system that I had in mind for part 2 turned out unsuited for publication. But part 2 will eventually come, I only don’t yet know when.

]]> By: Octavian https://financial-hacker.com/deep-learning-systems-for-bitcoins-part-1/#comment-69372 Tue, 26 Jan 2021 02:02:46 +0000 http://www.financial-hacker.com/?p=2899#comment-69372 This is excellent. Any chance of the part 2 of this article happening?

]]> By: jcl https://financial-hacker.com/deep-learning-systems-for-bitcoins-part-1/#comment-68471 Sun, 13 Dec 2020 16:58:55 +0000 http://www.financial-hacker.com/?p=2899#comment-68471 In reply to faustf.

Some places where you can get help for problems with C or R:

https://r-dir.com/community/forums.html
https://opserver.de/ubb7/
https://manual.zorro-project.com/
support@opgroup.de

]]> By: faustf https://financial-hacker.com/deep-learning-systems-for-bitcoins-part-1/#comment-68468 Sun, 13 Dec 2020 13:15:33 +0000 http://www.financial-hacker.com/?p=2899#comment-68468 hi i installed R and zorro and modify Zorro.ini

but why when i run this script
library(‘deepnet’)

neural.train = function(model,XY)
{
XY <- as.matrix(XY)
X <- XY[,-ncol(XY)]
Y <- XY[,ncol(XY)]
Y 0,1,0)
Models[[model]] <<- sae.dnn.train(X,Y,
hidden = c(30),
learningrate = 0.5,
momentum = 0.5,
learningrate_scale = 1.0,
output = "sigm",
sae_output = "linear",
numepochs = 100,
batchsize = 100)
}

neural.predict = function(model,X)
{
if(is.vector(X)) X <- t(X)
return(nn.predict(Models[[model]],X))
}

return me error library undecleared identifier deepnet ??

]]> By: jcl https://financial-hacker.com/deep-learning-systems-for-bitcoins-part-1/#comment-62247 Mon, 09 Sep 2019 09:14:09 +0000 http://www.financial-hacker.com/?p=2899#comment-62247 If your Ys are always positive, simply use ifelse(Y > Threshold,1,0). Select Threshold so that 1 and 0 are equally distributed.

]]> By: luca https://financial-hacker.com/deep-learning-systems-for-bitcoins-part-1/#comment-61958 Tue, 03 Sep 2019 08:11:47 +0000 http://www.financial-hacker.com/?p=2899#comment-61958 here ifelse(Y > 0,1,0), sorry again

]]> By: luca https://financial-hacker.com/deep-learning-systems-for-bitcoins-part-1/#comment-61957 Tue, 03 Sep 2019 08:10:55 +0000 http://www.financial-hacker.com/?p=2899#comment-61957 sorry, here correct statement Y 0,1,0)

]]> By: luca https://financial-hacker.com/deep-learning-systems-for-bitcoins-part-1/#comment-61956 Tue, 03 Sep 2019 08:09:58 +0000 http://www.financial-hacker.com/?p=2899#comment-61956 Hi, have a doubt about the following statement

Y 0,1,0)

in my dataset Y is equal to the close therefore always positive, should not be the percentage of variation?
thanks for any clarification.
Bye

]]>