Something to read

Forex for Beginners: A Beginner's Guide to Trading Tools and Tactics, Money Management, Secret of Martingale strategy, Candlestick patterns, Binary option secret, Success stories

If you would like to profit from trading the Forex markets but do not want to use large amounts of money to start - then this is the method for you. For as little as 200/USD to start trading you can make a regular income stream.

• Tools and Tactics
• Money Management
• Martingale strategy
• Candlestick patterns
• Success stories

In the previous article, we started learning association rules mining algorithms which belong to unsupervised learning methods. We have considered two algorithms for solving this type of problems: Apriori and FP Growth. The bottleneck of the Apriori algorithm is its large number of database calls aimed at determining the support of Frequent Pattern candidates. The FP Growth method solves this issue by building a tree which includes the entire database. All further operations are carried out with the FP tree, without accessing the database. This increases the problem solving speed, as the FP tree is located in RAM. Accessing it is much faster than a full iteration of the database.

more...

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

1. Neural networks made easy
2. Neural networks made easy (Part 2): Network training and testing
3. Neural networks made easy (Part 3): Convolutional networks
4. Neural networks made easy (Part 4): Recurrent networks
5. Neural networks made easy (Part 5): Multithreaded calculations in OpenCL
6. Neural networks made easy (Part 6): Experimenting with the neural network learning rate
7. Neural networks made easy (Part 7): Adaptive optimization methods
8. Neural networks made easy (Part 8): Attention mechanisms
9. Neural networks made easy (Part 9): Documenting the work
10. Neural networks made easy (Part 10): Multi-Head Attention
11. Neural networks made easy (Part 11): A take on GPT
12. Neural networks made easy (Part 12): Dropout
13. Neural networks made easy (Part 13): Batch Normalization
14. Neural networks made easy (Part 14): Data clustering
15. Neural networks made easy (Part 15): Data clustering using MQL5
16. Neural networks made easy (Part 16): Practical use of clustering
17. Neural networks made easy (Part 17): Dimensionality reduction
18. Neural networks made easy (Part 18): Association rules
19. Neural networks made easy (Part 19): Association rules using MQL5

We continue to study unsupervised learning methods. In previous articles, we have already analyzed clustering, data compression, and association rule mining algorithms. But the previously considered unsupervised algorithms do not use neural networks. In this article, we get back to studying neural networks. This time we will take a look at Autoencoders.

more...

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

1. Neural networks made easy
2. Neural networks made easy (Part 2): Network training and testing
3. Neural networks made easy (Part 3): Convolutional networks
4. Neural networks made easy (Part 4): Recurrent networks
5. Neural networks made easy (Part 5): Multithreaded calculations in OpenCL
6. Neural networks made easy (Part 6): Experimenting with the neural network learning rate
7. Neural networks made easy (Part 7): Adaptive optimization methods
8. Neural networks made easy (Part 8): Attention mechanisms
9. Neural networks made easy (Part 9): Documenting the work
10. Neural networks made easy (Part 10): Multi-Head Attention
11. Neural networks made easy (Part 11): A take on GPT
12. Neural networks made easy (Part 12): Dropout
13. Neural networks made easy (Part 13): Batch Normalization
14. Neural networks made easy (Part 14): Data clustering
15. Neural networks made easy (Part 15): Data clustering using MQL5
16. Neural networks made easy (Part 16): Practical use of clustering
17. Neural networks made easy (Part 17): Dimensionality reduction
18. Neural networks made easy (Part 18): Association rules
19. Neural networks made easy (Part 19): Association rules using MQL5
20. Neural networks made easy (Part 20): Autoencoders

We continue to study unsupervised learning methods. In the last article, we got acquainted with autoencoders. The topic of autoencoders is broad and cannot fit within one article. I would like to continue this topic and introduce you to one of autoencoder modifications — variational autoencoders.

more...

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

1. Neural networks made easy
2. Neural networks made easy (Part 2): Network training and testing
3. Neural networks made easy (Part 3): Convolutional networks
4. Neural networks made easy (Part 4): Recurrent networks
5. Neural networks made easy (Part 5): Multithreaded calculations in OpenCL
6. Neural networks made easy (Part 6): Experimenting with the neural network learning rate
7. Neural networks made easy (Part 7): Adaptive optimization methods
8. Neural networks made easy (Part 8): Attention mechanisms
9. Neural networks made easy (Part 9): Documenting the work
10. Neural networks made easy (Part 10): Multi-Head Attention
11. Neural networks made easy (Part 11): A take on GPT
12. Neural networks made easy (Part 12): Dropout
13. Neural networks made easy (Part 13): Batch Normalization
14. Neural networks made easy (Part 14): Data clustering
15. Neural networks made easy (Part 15): Data clustering using MQL5
16. Neural networks made easy (Part 16): Practical use of clustering
17. Neural networks made easy (Part 17): Dimensionality reduction
18. Neural networks made easy (Part 18): Association rules
19. Neural networks made easy (Part 19): Association rules using MQL5
20. Neural networks made easy (Part 20): Autoencoders
21. Neural networks made easy (Part 21): Variational autoencoders (VAE)

Our experiments have confirmed the effectiveness of autoencoder models. Pay attention that we used fully connected neural layers to train autoencoders. Such models work with a fixed input data window. The algorithm we have built can training any models operating with a fixed input data window. But the architecture of recurrent models is different. To make a decision on the activation of neurons, such models also use their previous state, in addition to the initial data. This feature should be taken into account when building an autoencoder.

more...

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

1. Neural networks made easy
2. Neural networks made easy (Part 2): Network training and testing
3. Neural networks made easy (Part 3): Convolutional networks
4. Neural networks made easy (Part 4): Recurrent networks
5. Neural networks made easy (Part 5): Multithreaded calculations in OpenCL
6. Neural networks made easy (Part 6): Experimenting with the neural network learning rate
7. Neural networks made easy (Part 7): Adaptive optimization methods
8. Neural networks made easy (Part 8): Attention mechanisms
9. Neural networks made easy (Part 9): Documenting the work
10. Neural networks made easy (Part 10): Multi-Head Attention
11. Neural networks made easy (Part 11): A take on GPT
12. Neural networks made easy (Part 12): Dropout
13. Neural networks made easy (Part 13): Batch Normalization
14. Neural networks made easy (Part 14): Data clustering
15. Neural networks made easy (Part 15): Data clustering using MQL5
16. Neural networks made easy (Part 16): Practical use of clustering
17. Neural networks made easy (Part 17): Dimensionality reduction
18. Neural networks made easy (Part 18): Association rules
19. Neural networks made easy (Part 19): Association rules using MQL5
20. Neural networks made easy (Part 20): Autoencoders
21. Neural networks made easy (Part 21): Variational autoencoders (VAE)
22. Neural networks made easy (Part 22): Unsupervised learning of recurrent models .....
23. Neural networks made easy (Part 23): Building a tool for Transfer Learning

We continue our immersion in the world of artificial intelligence. What is Transfer Learning and why do we need it? Transfer Learning is a machine learning method in which the knowledge of a model trained to solve one problem is reused as a basis for solving new problems. Of course, to solve new problems, the model is preliminarily additionally trained on new data. In the general case, with a properly selected donor model, additional training runs much faster and with better results than training a similar model from scratch.

more...

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

1. Neural networks made easy
2. Neural networks made easy (Part 2): Network training and testing
3. Neural networks made easy (Part 3): Convolutional networks
4. Neural networks made easy (Part 4): Recurrent networks
5. Neural networks made easy (Part 5): Multithreaded calculations in OpenCL
6. Neural networks made easy (Part 6): Experimenting with the neural network learning rate
7. Neural networks made easy (Part 7): Adaptive optimization methods
8. Neural networks made easy (Part 8): Attention mechanisms
9. Neural networks made easy (Part 9): Documenting the work
10. Neural networks made easy (Part 10): Multi-Head Attention
11. Neural networks made easy (Part 11): A take on GPT
12. Neural networks made easy (Part 12): Dropout
13. Neural networks made easy (Part 13): Batch Normalization
14. Neural networks made easy (Part 14): Data clustering
15. Neural networks made easy (Part 15): Data clustering using MQL5
16. Neural networks made easy (Part 16): Practical use of clustering
17. Neural networks made easy (Part 17): Dimensionality reduction
18. Neural networks made easy (Part 18): Association rules
19. Neural networks made easy (Part 19): Association rules using MQL5
20. Neural networks made easy (Part 20): Autoencoders
21. Neural networks made easy (Part 21): Variational autoencoders (VAE)
22. Neural networks made easy (Part 22): Unsupervised learning of recurrent models .....
23. Neural networks made easy (Part 23): Building a tool for Transfer Learning

In the previous article in this series, we have created a tool to take advantage of the Transfer Learning technology. As a result of the work done, we got a tool that allows the editing of already trained models.

Furthermore, the created tool allows not only editing trained models. It also allows creating completely new ones.

Such a useful toll should also be as user friendly as possible. Thus, in this article, we will try to improve its usability.

more...

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

1. Neural networks made easy
2. Neural networks made easy (Part 2): Network training and testing
3. Neural networks made easy (Part 3): Convolutional networks
4. Neural networks made easy (Part 4): Recurrent networks
5. Neural networks made easy (Part 5): Multithreaded calculations in OpenCL
6. Neural networks made easy (Part 6): Experimenting with the neural network learning rate
7. Neural networks made easy (Part 7): Adaptive optimization methods
8. Neural networks made easy (Part 8): Attention mechanisms
9. Neural networks made easy (Part 9): Documenting the work
10. Neural networks made easy (Part 10): Multi-Head Attention
11. Neural networks made easy (Part 11): A take on GPT
12. Neural networks made easy (Part 12): Dropout
13. Neural networks made easy (Part 13): Batch Normalization
14. Neural networks made easy (Part 14): Data clustering
15. Neural networks made easy (Part 15): Data clustering using MQL5
16. Neural networks made easy (Part 16): Practical use of clustering
17. Neural networks made easy (Part 17): Dimensionality reduction
18. Neural networks made easy (Part 18): Association rules
19. Neural networks made easy (Part 19): Association rules using MQL5
20. Neural networks made easy (Part 20): Autoencoders
21. Neural networks made easy (Part 21): Variational autoencoders (VAE)
22. Neural networks made easy (Part 22): Unsupervised learning of recurrent models .....
23. Neural networks made easy (Part 23): Building a tool for Transfer Learning
24. Neural networks made easy (Part 24): Improving the tool for Transfer Learning
25. Neural networks made easy (Part 25): Practicing Transfer Learning
26. Neural networks made easy (Part 26): Reinforcement Learning
27. Neural networks made easy (Part 27): Deep Q-Learning (DQN)
28. Neural networks made easy (Part 28): Policy gradient algorithm

We continue to study the Transfer Learning technology. In the previous two articles, we created a tool for creating and editing neural network models. This tool will help us transfer part of the pre-trained model to a new model and supplement it with new decision layers. We will also check the usability of our tool.

more...

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

1. Neural networks made easy
2. Neural networks made easy (Part 2): Network training and testing
3. Neural networks made easy (Part 3): Convolutional networks
4. Neural networks made easy (Part 4): Recurrent networks
5. Neural networks made easy (Part 5): Multithreaded calculations in OpenCL
6. Neural networks made easy (Part 6): Experimenting with the neural network learning rate
7. Neural networks made easy (Part 7): Adaptive optimization methods
8. Neural networks made easy (Part 8): Attention mechanisms
9. Neural networks made easy (Part 9): Documenting the work
10. Neural networks made easy (Part 10): Multi-Head Attention
11. Neural networks made easy (Part 11): A take on GPT
12. Neural networks made easy (Part 12): Dropout
13. Neural networks made easy (Part 13): Batch Normalization
14. Neural networks made easy (Part 14): Data clustering
15. Neural networks made easy (Part 15): Data clustering using MQL5
16. Neural networks made easy (Part 16): Practical use of clustering
17. Neural networks made easy (Part 17): Dimensionality reduction
18. Neural networks made easy (Part 18): Association rules
19. Neural networks made easy (Part 19): Association rules using MQL5
20. Neural networks made easy (Part 20): Autoencoders
21. Neural networks made easy (Part 21): Variational autoencoders (VAE)
22. Neural networks made easy (Part 22): Unsupervised learning of recurrent models .....
23. Neural networks made easy (Part 23): Building a tool for Transfer Learning
24. Neural networks made easy (Part 24): Improving the tool for Transfer Learning
25. Neural networks made easy (Part 25): Practicing Transfer Learning
26. Neural networks made easy (Part 26): Reinforcement Learning
27. Neural networks made easy (Part 27): Deep Q-Learning (DQN)
28. Neural networks made easy (Part 28): Policy gradient algorithm

In the previous article, we started exploring reinforcement learning methods and built our first cross-entropy trainable model. In this article, we continue to study reinforcement learning methods. We will proceed to the Deep Q-Learning method.

more...

In the previous articles of this series, we have already seen supervised and unsupervised learning algorithms. This article opens another machine learning chapter: Reinforcement Learning.

more...