|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/machine-learning-in-physics-glass-identification-problem/
课程评论：没有评论
课程名称：物理中的机器学习：玻璃识别问题 课程概述：将您的机器学习技能从理论转向实践，探索物理学中最有趣的领域之一。在本课程中，您将解决玻璃识别问题，构建和训练多个机器学习模型，以分类七种类型的玻璃，包括建筑窗户浮法玻璃、建筑窗户非浮法玻璃、车辆窗户浮法玻璃、车辆窗户非浮法玻璃、容器玻璃、餐具玻璃和车灯玻璃。通过这门课程，您将学习如何从头到尾处理机器学习问题： 1. 导入、探索、分析和可视化数据。 2. 学习数据预处理的不同技术，如数据清洗、数据缩放和数据分割，以便为模型提供最合适的数据格式。 3. 构建和训练一系列机器学习模型，如逻辑回归、支持向量机（SVM）、决策树和随机森林分类器。 4. 评估和测量模型性能的不同指标，如准确率和混淆矩阵。 5. 比较不同模型的结果。 6. 微调模型以提升其性能。 完成本课程后，您将掌握处理任何机器学习问题所需的技能，从最初步骤到获得一个完全训练好的高效模型。
Move your ML skills from theory to practice in one of the most interesting fields " Physics"? In this course you are going to solve the glass identification problem where you are going to build and train several machine learning models in order to classify 7 types of glass( 1- Building windows float-processed glass / 2- Building windows non-float-processed glass / 3- Vehicle windows float-processed glass / 4- Vehicle windows non-float-processed-glass / 5- Containers glass / 6- Tableware glass / 7- Headlamps glass). Through this course, you will learn how to deal with a machine learning problem from start to end: 1 - You will learn how to import, explore, analyze and visualize your data. 2- You will learn the different techniques of data preprocessing like: data cleaning, data scaling and data splitting in order to feed the most convenient format of data to your models. 3- You will learn how to build and train a set of machine learning models such as: Logistic Regression, Support Vector Machine (SVM), Decision Trees and Random Forest Classifiers.4- You will learn how to evaluate and measure the performance of your models with different metrics like: accuracy-score and confusion matrix.5- You will learn how to compare between the results of your models.6- You will learn how to fine-tune your models to boost their performance.After completing this course, you will gain a bunch of skillset that allows you to deal with any machine learning problem from the very first step to getting a fully trained performent model.
