What you'll learn

Introduction to Data science

Introduction to Artificial intelligence

Introduction to Machine learning

Coding Neural networks in MQL5

Training Neural Networks in MQL5

Requirements

MQL5 Beginner knowledge

Description

In this course, our primary objective is to introduce you to the realm of Machine learning with neural networks using the most powerful algorithmic trading language, MQL5. Our aim is to give you a solid foundation to principles and concepts you will need in developing self optimizing softwares that learn from data the same way that the human brain learns.This course is structured for complete beginners to machine learning. There is no prior knowledge of statistics, linear algebra or complex mathematical understanding needed. You will be breast fed everything and we will simplify all processes and content without eliminating its value or impact in your learning.In this course, we shall first introduce you to data science and how it relates to artificial intelligence and machine learning. Then we shall take a closer look at machine learning and the types of models involved in machine learning processes. I shall then briefly introduce you to the world of Neural networks, the types of neural networks commonly used in algorithmic trading and the processes involved in designing a neural network model.To get an idea of the concepts and processes involved in neural network calculations, training and prediction, we shall build a very simple neural network in excel from scratch and train it to identify a buy signal from the RSI indicator and Moving average. This will be very useful in helping you understand the foundation of supervised learning with neural networks, enabling you to follow through the MQL5 coding process with ease.In this course, we shall use matrices and vector data types instead of simple arrays to store most of our data. So we shall introduce you to these new datatypes from scratch by looking at their declaration, their initialization and how to manipulate them.We shall then code a neural network on MQL5 from scratch, which aims to find hidden patterns in the RSI and Bollinger band indicators that are suggestive of a bullish market or a bearish market. We shall do this by training our neural network using back propagation to identify and classify the market into bullish and bearish classes.Join us in this course and prepare to be astonished by the sheer power of neural networks. This course is not for the faint of heart, but for those who dare to explore the boundless frontiers of artificial intelligence. Prepare to be challenged, immersed, and captivated as you embark on this intellectual adventure.So Click that enroll button now!! And Unleash your curiosity,

Overview

Section 1: Overview of Machine learning

Lecture 1 Data science, Artificial intelligence and Machine learning

Lecture 2 Types of Machine learning

Lecture 3 Introduction to Neural Networks

Lecture 4 Feed Forward Neural Network Architecture

Section 2: Introduction to Neural Networks

Lecture 5 ForwardPass on a spreadsheet

Lecture 6 Mean squared error on a spread sheet

Lecture 7 Backward pass on a spread sheet

Lecture 8 Gradient descent on a spread sheet

Section 3: Vector and Matrix Datatypes

Lecture 9 Linear Algebra, Vectors and Matrices

Lecture 10 Declaring Matrices and Vectors

Lecture 11 Initializing Matrices and Vectors

Lecture 12 Copying Data into Matrices and Vectors

Lecture 13 Copying Timeseries Data into Matrices and Vectors

Lecture 14 Matrices and Vector Operations

Lecture 15 Manipulating Matrices

Section 4: Data Collection

Lecture 16 Neural Network Architecture

Lecture 17 General EA parameters

Lecture 18 Setting the Live calculation interval

Lecture 19 Creating Data Vessels

Lecture 20 Initializing Handles

Lecture 21 Collecting indicator Data

Lecture 22 Data Normalization

Lecture 23 Initializing Weights and Bias

Section 5: Forward Pass

Lecture 24 Converting Matrices to Vectors

Lecture 25 Converting Vectors to Matrices

Lecture 26 Neuron Calculations

Lecture 27 Forward Function

Section 6: Neural Network Training

Lecture 28 Searching for Patterns

Lecture 29 Removing an index from a Vector

Lecture 30 Removing Matrix Rows and Columns

Lecture 31 Confusion Matrix Declaration

Lecture 32 Populating the Confusion Matrix

Lecture 33 Model Accuracy and Precision

Lecture 34 Recall / Sensitivity Calculation

Lecture 35 Specificity calculation

Lecture 36 F1 Score calculation

Lecture 37 Support calculation

Lecture 38 Predictive Metrics averages

Lecture 39 Creating Data classes

Lecture 40 One Hot Encoding

Lecture 41 Loss Function Options

Lecture 42 Batch Forward Pass

Lecture 43 Back Propagation training

Lecture 44 Prediction Presentation

Lecture 45 Model Training

Section 7: Model Testing

Lecture 46 Displaying Probability Signals

Lecture 47 Visually testing the model

Lecture 48 Assignment

Section 8: Conclusion

Lecture 49 Conclusion

Anyone wishing to use machine learning in algorithmic trading