Discussion of article "Deep Neural Networks (Part IV). Creating, training and testing a model of neural network"
Thanks Vladimir! the series is great, the tools introduced is really helpful. I have been experimenting on some indices, the result is more or less, overall slightly better. I have tried the "bin" input for darch, it's similar to "woe", while the "dum" is bad. maybe too many input is not a good thing.
"Tensorflow" package sounds promising. can't wait for the article!
Спасибо, Владимир! серия отличная, инструменты, представленные, действительно полезны. Я экспериментировал по некоторым показателям, результат более или менее, в целом немного лучше. Я попробовал вход «bin» для darch, он похож на «горький», в то время как «dum» плохой. возможно, слишком много ввода не очень хорошо.
Пакет «Tensorflow» звучит многообещающе. не могу дождаться статьи!
Oh. The last three parts of the article are almost ready. Maybe before the New Year I'll have time to pass on for verification.
Good luck
- An R package by Holger K. von Jouanne-Diedrich
- cran.r-project.org
Благодарим вас за использование моего пакета OneR. Еще раз увлекательно видеть, что даже сложный DNN не намного лучше, чем модель OneR!
This is only true for DNN with default parameters. With optimized hyperparameters, DNN shows much better results. See Part V.
Good luck
This is only true for DNN with default parameters. With optimized hyperparameters, DNN shows much better results. See Part V.
Good luck
![MQL5 - Language of trade strategies built-in the MetaTrader 5 client terminal](https://c.mql5.com/i/registerlandings/logo-2.png)
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
You agree to website policy and terms of use
New article Deep Neural Networks (Part IV). Creating, training and testing a model of neural network has been published:
This article considers new capabilities of the darch package (v.0.12.0). It contains a description of training of a deep neural networks with different data types, different structure and training sequence. Training results are included.
The trained neural network can be trained further on new data as many times as required. This is possible only with a limited number of models. Structural diagram of a deep neural network initialized by complex restricted Boltzmann machines (DNRBM) is shown on Fig.2.
Fig.2. Structural diagram of DNSRBM
Author: Vladimir Perervenko