|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/machine-learning-optimization-using-genetic-algorithm/
课程评论：没有评论
课程名称：使用遗传算法进行机器学习优化 课程概述：本课程将教授您超参数的概念、遗传算法的原理以及超参数优化的技巧。通过本课程，您将运用遗传算法来优化支持向量机（SVM）和多层感知器神经网络（MLP NN）的性能，通常称为超参数调优或参数调优。您还将学习如何利用遗传算法进行特征选择。 课程中将对两个数据集进行超参数优化： 1. 预测建筑物冷负荷和热负荷的回归数据集 2. 对邮件进行垃圾邮件和非垃圾邮件分类的分类数据集 课程将展示在应用SVM和MLP时，没有优化和进行了优化的结果比较。同时，将在一个数据集上进行特征选择，该数据集用于区分良性肿瘤与恶性肿瘤。 通过本课程，您将学习如何在Python中编写遗传算法代码，并优化您的机器学习算法以实现最佳性能。同时，您还将了解如何运用遗传算法进行特征选择。 总结课程内容： - 理解什么是超参数（与参数不同） - 学习遗传算法的基本原理 - 使用遗传算法优化机器学习算法的性能 - 最大化模型的准确性和预测能力 - 优化SVM和MLP神经网络的性能 - 应用特征选择提取与预测输出相关的特征 - 去除冗余特征，从而降低模型的时间和复杂性 - 理解哪些特征与输出相关，哪些不相关 本课程不要求您具备太多优化或Python编程的知识和经验，但有一些基础会有所帮助。课程中的每一行代码都有详细的解释，以简单明了的方式展示如何编写遗传算法代码，即使您对Python没有任何基础也能成功。 值得一提的是，这并不仅仅是一门教您如何优化机器学习模型的课程，同时也是一门Python编程课程！ 对于任何问题，请随时询问！如果您对课程不满意，可以申请30天退款！
In this course, you will learn what hyperparameters are, what Genetic Algorithm is, and what hyperparameter optimization is. In this course, you will apply Genetic Algorithm to optimize the performance of Support Vector Machines (SVMs) and Multilayer Perceptron Neural Networks (MLP NNs). It is referred to as hyperparameter tuning or parameter tuning. You will also learn how to do feature selection using Genetic Algorithm.Hyperparameter optimization will be done on two datasets:A regression dataset for the prediction of cooling and heating loads of buildingsA classification dataset regarding the classification of emails into spam and non-spamThe SVM and MLP will be applied on the datasets without optimization and compare their results to after their optimizationFeature Selection will be done on one dataset:Classification of benign tumors from malignant tumors in a breast cancer datasetBy the end of this course, you will have learnt how to code Genetic Algorithm in Python and how to optimize your machine learning algorithms for maximum performance. You would have also learnt how to apply Genetic Algorithm for feature selection.To sum up:You will learn what hyperparameters are (sometimes referred to as parameters, though different)You will learn Genetic AlgorithmYou will use Genetic Algorithm to optimize the performance of your machine learning algorithmsMaximize your model's accuracy and predictive abilitiesOptimize the performance of SVMs and MLP Neural NetworksApply feature selection to extract the features that are relevant to the predicted outputGet the best out of your machine learning modelRemove redundant features, which in return will reduce the time and complexity of your modelUnderstand what are the features that have a relationship to the output and which do notYou do not need to have a lot of knowledge and experience in optimization or Python programming - it helps, but not a must to succeed in this course.This course will teach you how to optimize the functionality of your machine learning algorithmsWhere every single line of code is explained thoroughlyThe code is written in a simple manner that you will understand how things work and how to code Genetic Algorithm even with zero knowledge in PythonBasically, you can think of this as not only a course that teaches you how to optimize your machine learning model, but also Python programming!Please feel free to ask me any question! Don't like the course? Ask for a 30-day refund!!Real Testaments ->1) "This is my second course with Dana. This course is a combination of Metaheuristic and machine learning. It gives a wide picture of machine learning hyperparameter optimization. I recommend taking this course if you know basics of machine learning and you want to solve some problems using ML. By applying the techniques of GA optimization, you will have better performance of ML. The codes provided in this course are very straightforward and easy to understand. The course deserves five stars because of the lecture contents and examples. The instructor knowledgeable about the topic and talented in programming." - Abdulaziz, 5 star rating2) "An excellent course! Great for anyone interested in fine-tuning their machine-learning models. I really enjoyed the from scratch implementations and how well they are explained. These implementations from scratch help one understand the theory very well. An interesting thing to point out is that this course uses Metaheustistics to optimise machine-learning. However, you can use machine-learning classifiers to help your Metaheuristic predict good or bad regions." - Dylan, 5 star rating3) "Very helpful, for application of optimization algorithm to optimize ML algorithm parameters and got to do this using python, wonderful." - Erigits, 5 star rating4) "well explained course. The topic is not an easy one but to date the explanations have been clear. The course has an interesting spreadsheet project." - Martin, 5 star rating5) "Thank you very much for this awesome course. Lots of new things learn from this course." - Md. Mahmudul, 5 star rating
