Neural Networks - page 26

[Sergey Golubev]

What to read and where to learn about Machine Learning

 

Форум по трейдингу, автоматическим торговым системам и тестированию торговых стратегий

What to read and where to learn about Machine Learning

MetaQuotes Software Corp., 2017.08.25 11:37

There are 10 free books related to machine Learning (based on thepixelbeard.com portal.

1. The Elements Of Statistical Learning : Data Mining, Inference and Prediction

This is an ebook by T.Hastie, R. Tibshirani, J.Friedman that lets readers get knowledge about conceptual underpinnings. There are varied topics included like statistical framework and much more.

2. Inductive Logical Programming

Inductive logic programming is a topic in Machine Learning. It is used in research field at the intersection of machine learning and logic programming.

3. Reinforcement Learning : An introduction by Richard S. Sutton, Andrew G. Barto

This is an ebook written by Richard S. Sutton, Andrew G. Barto. With this ebook users can get a grasp of machine learning the easy way.

4. Information Theory, Inference and Learning Algorithms

This is an ebook by David J.C. Mackay in which information theory topic is well explained in such a way that it helps readers attain good knowledge about the practical communication systems viz. arithmetic coding for data compression, sparse-graph codes for error-correction and more.

5. Gaussian Processes for Machine Learning

This is an ebook by Carl E. Rasmussen, Chritopher K.I Williams. With this ebook one can learn a principled, practical, probabilistic approach to learning in kernel machines in quite a simple way.

6. The LION Way

This ebook is written by Roberto Battiti, Mauro Brunato and has been written in such a way that it helps users in machine learning and Intelligent Optimization (LION).

7. Bayesian Reasoning and Machine Learning

This is an ebook that is written by David Barber that targets the final-year undergraduates and master’s students. The topics include linear algebra and calculus. This book helps users learn basic reasoning, advanced techniques within the framework of graphical models and develop skills.

8. A Course In Machine Learning

This ebook by Hal Daume III is a course book that includes a set of introductory material covering different aspects of modern machine learning.

9. Machine Learning, Neural And Statistical Classification

This is an ebook by D. Michie, D.J Spiegelhalter that aims at providing an up-to-date review of different approaches to classification.

10. Introduction To Machine Learning

This ebook is written by Nilis J Nilsson. It includes different topics in machine learning circa 1996 that helps people pursue a middle ground between theory and practice.

[Sergey Golubev]

Neural Network

Neural Network: discussion/development threads

1. Better NN EA development thread with indicators, pdf files and so on.
2. Better NN EA final thread 
3. taking NEURAL NETWORKS to the NEXT LEVEL - very interesting thread
4. Neural Networks thread (good public discussion)
5. How to build a NN-EA in MT4: usefull thread for developers.
6. Radial Basis Network (RBN) - As Fit Filter For Price: the thread 

Neural Network: Indicators and systems development

1. Self-trained MA cross!: development thread for new generation of the indicators
2. Levenberg-Marquardt algorithm: development thread

Neural Network: EAs

1. CyberiaTrader EA: discussion thread and EAs' thread.
2. Self learning expert thread with EAs' files here.
3. Artificial Intelligence EAs threads: How to "teach" and to use the AI ("neuron") EA thread and Artificial Intelligence  thread
4. Forex_NN_Expert EA and indicator thread.
5. SpiNNaker - A Neural Network EA thread. 

Neural Network: The Books

1. What to read and where to learn about Machine Learning (10 free books) - the post.

The article

• Neural Networks Made Easy - MT5
  
• Neural networks made easy (Part 2): Network training and testing - MT5
  
• Machine learning in Grid and Martingale trading systems. Would you bet on it? - MT5
  
• Neural networks made easy (Part 3): Convolutional networks - MT5
  
• Neural networks made easy (Part 4): Recurrent networks - MT5 
• Neural networks made easy (Part 5): Multithreaded calculations in OpenCL - MT5 
• Neural networks made easy (Part 6): Experimenting with the neural network learning rate - MT5 
• Neural networks made easy (Part 7): Adaptive optimization methods - MT5 
• Neural networks made easy (Part 8): Attention mechanisms - MT5
• Neural networks made easy (Part 9): Documenting the work - MT5
  
• Neural networks made easy (Part 10): Multi-Head Attention - MT5
  
• Neural networks made easy (Part 11): A take on GPT - MT5
  
• Neural networks made easy (Part 12): Dropout - MT5
  
• Neural networks made easy (Part 13): Batch Normalization - MT5
  
• Developing a self-adapting algorithm (Part I): Finding a basic pattern  - MT5
  
• Developing a self-adapting algorithm (Part II): Improving efficiency  - MT5
  
• Self-adapting algorithm (Part III): Abandoning optimization - MT5
  
• Deep neural network with Stacked RBM. Self-training, self-control - MT4 
• Practical application of neural networks in trading - MT5
  
• Practical application of neural networks in trading. Python (Part I) - MT5
  
• Practical application of neural networks in trading (Part 2). Computer vision - MT5
  
• Connecting NeuroSolutions Neuronets - MT5
• Using Neural Networks In MetaTrader - MT4
• Price Forecasting Using Neural Networks - MT4
• Recipes for Neuronets - MT4
• Third Generation Neural Networks: Deep Networks - MT5
• Neural Networks Cheap and Cheerful - Link NeuroPro with MetaTrader 5 - MT5
• Creating Neural Network EAs Using MQL5 Wizard and Hlaiman EA Generator - MT5
• Neural network: Self-optimizing Expert Advisor - MT5
• Neural Networks: From Theory to Practice - MT5
• Using MetaTrader 5 Indicators with ENCOG Machine Learning Framework for Timeseries Prediction - MT5
• Using Self-Organizing Feature Maps (Kohonen Maps) in MetaTrader 5 - MT5
• Deep Neural Networks (Part I). Preparing Data - MT5

• Deep Neural Networks (Part II). Working out and selecting predictors - MT5

CodeBase

• Next price predictor using Neural Network - indicator for MetaTrader 4
• Easy Neural Network - library for MetaTrader 5
  
• ALGLIB - Numerical Analysis Library - library for MetaTrader 4
• MTS Neural network plus MACD - expert for MetaTrader 4
• ArtificialIntelligence_Right - expert for MetaTrader 4
• NeuroNirvamanEA - expert for MetaTrader 4
• Create your own neural network predictor easily (example: MA and RSI Predictors) - indicator for MetaTrader 4
• Automated Trading System "Сombo" - expert for MetaTrader 4
• MTC Neural network plus MACD - expert for MetaTrader 5
• Bollinger Band Width calculation with Neural Network using - expert for MetaTrader 5
• PNN Neural Network Class - library for MetaTrader 5
• GRNN Neural Network Class - library for MetaTrader 5
• RBF Neural Network Class - library for MetaTrader 5
• MLP Neural Network Class - library for MetaTrader 5
• Artificial Intelligence - expert for MetaTrader 5

[Sergey Golubev]

New article - 

Deep Neural Networks (Part III). Sample selection and dimensionality reduction

Contents

• Introduction
• 1. Sample selection 
  
• 2. Dimensionality reduction 
  
• 2.1. Principal component analysis (PCA)
• 2.2. Independent component analysis (ICA)
• 2.3. Probabilistic principal component analysis (PPCA)
• 2.4. Autoencoder (nonlinear PCA) 
  
• 2.5. Inverse nonlinear PCA (NLPCA)
• 3. Dividing the data set into the train/valid/test sets
• Conclusion
• Application

[Sergey Golubev]

Next article - 

Deep Neural Networks (Part IV). Creating, training and testing a model of neural network

Contents

• Introduction
• 1. Brief description of the package capabilities
• 1.1. Initialization functions of neurons
• 1.2. Activation functions of neurons
• 1.3. Training methods
• 1.4. Methods of regulation and stabilization
• 1.5. Methods and parameters of training an RBM
• 1.6. Methods and parameters of training a DNN
• 2. Testing the quality of work of a DNN depending on the used parameters
• 2.1. Experiments
• 2.1.1. Input data (preparation)
• 2.1.2. Basic model of comparison
• 2.1.3. Structure of a DNN
• 2.1.4. Variants of training
• With pretraining
• Without pretraining
• 2.2. Result analysis
• Conclusion
• Application

[Sergey Golubev]

Taking NEURAL NETWORKS to the NEXT LEVEL - very interesting thread:

This thread won't be about a question or problem, but rather about the anouncement of the presentation and documentation of an exciting trading concept. I plan to do a series of postings here in order to keep you guys updated.

Anybody who has an opinion on the topic, please don't hesitate to comment, even if you don't have profound machine learning knowledge (I'm still learning, too - which never ends).

[Chris70]

Sergey Golubev:

Taking NEURAL NETWORKS to the NEXT LEVEL - very interesting thread:

thanks, Sergey; I'm the starter of that thread; I wasn't aware of those two articles (above) that you linked in Oct2017. The topics are extremily close to each other, so I realize that I was being a little redundant. I will continue the series nevertheless, because I think the aspect LSTM+autoencoder might still be of interest.

[Sergey Golubev]

Forum on trading, automated trading systems and testing trading strategies

How to Start with Metatrader 5

Sergey Golubev, 2020.03.12 06:42

Neural Networks Made Easy - MT5 

Table of Contents

• Introduction
• 1. AI network building principles
• 2. The structure of an artificial neuron
• 3. Network training
• 4. Building our own neural network using MQL
• 4.1. Connections
• 4.2. A neuron
• 4.3. Neural network
• Conclusion
• References
• Programs used in the article

The Artificial Intelligence is increasingly covering various aspects of our life. A lot of new publications appear, stating that "the neural network was trained to..." However, artificial intelligence is still associated with something fantastic. The idea seems to be very complicated, supernatural and inexplicable. Therefore, such a state-of-the art miracle can only be created by a group of scientists. It seems that a similar program cannot be developed using our home PC. But believe me, it's not that difficult. Let us try to understand what the neural networks are and how they can be applied in trading.

[Sergey Golubev]

Easy Neural Network - library for MetaTrader 5

The provided test script has included comments which are easy to follow along.

You can save the returned network configuration in a file then load it in different sessions.

This library has made little use of OOP, and should therefore be easy to follow along even by newer programmers.

[Sergey Golubev]

Practical application of neural networks in trading - the article for MT5

----------------

This article considers the application of neural networks when creating trading robots. This is the narrow sense of this problem. More broadly, we will try to answer some questions and to address several problems:

1. Can a profitable system be created using machine learning?
2. What can a neural network give us?
3. The rationale for training neural networks for decision making.
4. Neural Network: is it difficult or simple?
5. How to integrate a neural network into a trading terminal?
6. How to test a neural network? Testing stages.
7. About training samples.

[Sergey Golubev]

This is the 3rd article:

Neural networks made easy (Part 3): Convolutional networks  - MT5  

Contents

• Introduction
• 1. Distinctive features of convolutional neural networks
• 1.1. Convolutional layer
• 1.2. Subsampling layers
• 2. Principles of training neurons in convolutional layers
• 3. Building a convolutional neural network
• 3.1. Base class of neurons
• 3.1.1. Feed-forward
• 3.1.2. Error gradient calculation
• 3.2. Subsampling layer element
• 3.2.1. Feed-forward
• 3.2.2. Error gradient calculation
• 3.3. Convolutional layer element
• 3.4. Creating a convolutional neural network class
• 3.4.1. Convolutional neural network class constructor
• 3.4.2. Convolutional neural network forward propagation method
• 3.4.3. Convolutional neural network backward propagation method
• 4. Testing
• Conclusion
• List of references
• Programs used in the article

----------------

Previous two articles related to this subject:

• Neural Networks Made Easy - MT5 
  
• Neural networks made easy (Part 2): Network training and testing - MT5