|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/mql5-machine-learning-02-deep-learning-for-algo-trading/
课程评论：没有评论
Course Name: MQL5 机器学习 02: 深度学习用于算法交易 **课程概述:** 本课程是关于使用MQL5语言为外汇交易开发深度神经网络（DNN）的进阶课程。课程旨在解决传统算法交易方法在外汇市场动态数据分析中的局限性，并介绍深度学习的强大能力。 **核心内容:** * **深度学习的优势**: 课程将DNN比作一个协同工作的分析师团队，能够处理单层感知器（Perceptron）无法解决的复杂问题，能够挖掘隐藏在海量数据中的趋势和相关性。 * **实践基础（Excel）**: 首先，课程将引导学员在Excel中构建一个基础的DNN，重点介绍前向传播、反向传播（用于更新权重和偏差）以及梯度下降（用于训练网络）。这个环节旨在为后续的MQL5编程打下坚实基础，并处理实际的外汇交易问题。 * **MQL5实践**: 随后，课程将深入讲解如何在MQL5中编码DNN。内容包括： * **网络设计和参数设置** * **数据存储（Tensor）** * **数据收集与准备（数据随机化和标准化）** * **MQL5中的前向传播和反向传播实现** * **信号提取和预测可视化** **学习目标**: 完成本课程后，学员将不仅理解DNN的理论知识，更能独立运用MQL5编码实现DNN，并将其应用于外汇算法交易。 **目标受众**: 已具备神经网络基础知识，希望在外汇交易领域深入应用深度学习技术的交易者和开发者。
The forex market, a dynamic beast fueled by a complex web of data, demands a keen eye for intricate patterns and the agility to adapt. While traditional methods have served us well, their limitations become apparent in this ever-evolving landscape. These limitations have been overcome by the development of Deep Neural Networks (DNNs), a revolutionary approach poised to transform the forex trading landscape.In the previous courses on Neural networks, we only managed to create perceptrons, by taking input data, passing it through activation functions and getting outputs or predictions. These basically did hidden layer calculations without actual hidden layers. Hence we can liken perceptrons to single or lone traders who analyze charts, limited by its ability to do more work and specialize. Deep NNs, however, are like a collaborative team of analysts. With Information flowing from one expert analyst to another through their layered architecture, each layer building upon the insights or work done by the previous one. It's like a team identifying specific puzzle pieces, working together to reveal the bigger picture with remarkable clarity.This layered structure empowers DNNs to tackle problems that would leave a single perceptron incompetent. They excel at unveiling hidden trends, sifting through vast datasets and uncovering hidden correlations and patterns that escape the human eye. A DNN, by analyzing a broader range of data points and their relationships, could potentially identify small data relationships and adjust predictions accordingly.This course builds on your existing knowledge of neural networks to take you on a deep dive into Deep Neural Networks (DNNs) for forex trading. You'll learn to code your own DNNs using MQL5, a programming language for MetaTrader platforms.We'll start with a basic DNN built in Excel, providing a foundation for the more complex coding in MQL5. This hands-on exercise will focus on a real-world forex trading problem, showcasing the practical applications of DNNs. In Excel, you'll explore the forward pass, backpropagation for updating weights and biases, and gradient descent for training the network.Equipped with this knowledge, you'll transition to coding DNNs in MQL5. We'll cover designing the network, setting general parameters, and constructing a tensor for data storage. You'll learn to collect and prepare input data, including randomization and normalization. The course will then guide you through the forward pass and backpropagation in MQL5, along with extracting signals and visualizing predictions. By the end, you'll not only understand the theory of DNNs but also be able to code them for forex trading.So what are you waiting for? Click hard on that enroll button now and join us in this wonderful journey of coding a deep neural network in MQL5
