|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/supervised-machine-learning-principles-and-practices-python/
课程评论：没有评论
课程名称：《监督机器学习原理与实践- Python》 课程概述： 本课程介绍了机器学习的概念以及不同学习方法的分类，包括监督学习、无监督学习和强化学习。课程中将介绍一些流行的机器学习技术，并在Python中实现这些技术。 我们首先讨论决策树方法，简单明了地说明所需的数学工具，如熵，并通过Python进行实际实现，解释如何提高模型的准确性。接着，课程介绍了线性回归，通过简单的现实生活实例进行讲解，包含L2误差估计，并阐述如何利用梯度优化方法来最小化误差，同样使用Python库进行实现。 在课程中，我们还将通过实例讲解逻辑回归方法，并在Python中进行实现。邻近算法（Nearest Neighbourhood）也会被解释并应用于实际案例。支持向量机（SVM）是一种热门的监督学习模型，适用于分类或回归任务。该方法在高维空间中效果良好，并能有效处理小数据集。在训练数据集后，算法能够高效地对新观察值进行分类。 此外，我们还介绍了一些其他方法，如贝叶斯分类模型，用于处理大的有限数据集。这种方法通过一个有向无环图（DAG）来分配类别标签，图由一个父节点和多个子节点组成。每个子节点被假设为独立与父节点。贝叶斯模型因其简洁易用，在处理非常小的数据集时表现出色，并以常见的数据假设为基础，如每个特征之间相互独立。尽管存在这样的简化，该算法仍能在复杂问题上有效实现。 总之，此课程将帮助学生理解监督机器学习的核心原理，并提供实际编程训练，利用Python进行多种机器学习技术的实现。
In this course, we present the concept of machine learning and the classification of different methods of learning such as Supervised and Unsupervised Learning. We also present reinforcement learning. We offer popular techniques and implement them in Python. We begin with the Decision Tree method. We present this simply with all the required mathematical tools such as entropy. We implement them in Python and explain how the accuracy can be improved. We offer the classification problem with a suitable real-life scenario. Linear Regression is taught using simple real-life examples. We present the L2 Error estimation and explain how we can minimize the error using gradient optimization. This is implemented using the Python library. We also offer the Logistic Regression method with an example and implement in Python. The Nearest Neighbourhood approach is explained with examples and implemented in Python. Support Vector Machines (SVM) are a popular supervised learning model that you can use for classification or regression. This approach works well with high-dimensional spaces (many features in the feature vector) and can be used with small data sets effectively. When trained on a data set, the algorithm can easily classify new observations efficiently. We also present a few more methods. The Bayesian model of classification is used for large finite datasets. It is a method of assigning class labels using a direct acyclic graph. The graph comprises one parent node and multiple children nodes. And each child node is assumed to be independent and separate from the parent. As the model for supervised learning in ML helps construct the classifiers in a simple and straightforward way, it works great with very small data sets. This model draws on common data assumptions, such as each attribute is independent. Yet having such simplification, this algorithm can easily be implemented on complex problems.
