|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/machine-learning-from-zero-to-hero-introduction-to-ml/
课程评论：没有评论
课程名称：机器学习：从零到英雄（1）：机器学习导论 课程概述：机器学习：从零到英雄是一系列旨在帮助任何希望成为机器学习工程师、深度学习工程师、数据科学家或人工智能工程师的课程。本系列从科学和实践两个主要视角来探讨机器学习。我们提供每个机器学习概念所需的科学知识，同时避免不必要的细节。这种方法帮助学习者准确了解如何使用、实现和开发机器学习模型，最大限度地减少试错所花费的时间。第二个视角是实践，使学习者能够从零开始实现机器学习模型，深入理解它们的运行方式，并使用像Scikit-learn这样的包中的现成机器学习模型。这些视角确保学习者成为熟练的机器学习工程师、深度学习工程师、数据科学家和人工智能工程师。 该系列的第一门课程是：机器学习导论。这不仅仅是你见过的任何机器学习入门课程；它是一门全面而详细的课程，因此被作为独立的课程提供。在这门全面的导论课程中，你将学习以下内容： 1. 什么是人工智能（AI）？ 2. 人工智能与数据科学（DS）的区别是什么？ 3. 什么是软计算（SC）？ 4. 机器学习（ML）究竟是什么？ 5. 我们为什么需要机器学习？ 6. 什么是深度学习（DL）？ 7. 机器学习的应用。 8. 机器学习类型：基于监督程度的分类。 - 8.1 监督学习 - 8.1.1 回归 - 8.1.2 分类 - 8.2 无监督学习 - 8.2.1 聚类 - 8.2.2 异常检测 - 8.2.3 降维 - 8.2.4 关联规则 - 8.3 半监督学习 - 8.4 自监督学习 - 8.5 强化学习 9. 机器学习类型：基于系统是否能够从流入数据中增量学习。 - 9.1 批量学习 - 9.2 增量学习 10. 机器学习类型：基于学习的泛化方式。 - 10.1 实例基础学习 - 10.2 模型基础学习 11. Python实例： - 11.1 应用模型基础学习解决线性回归问题 - 11.2 应用实例基础学习解决线性回归问题 - 11.3 应用模型基础学习解决分类问题 - 11.4 应用实例基础学习解决分类问题 这门课程为学习机器学习奠定了坚实的基础，适合各个层次的学习者。
Machine Learning: From Zero to Hero is a series of courses designed for anyone looking to start a career as an ML engineer, DL Engineer, data scientist, or AI engineer.This series approaches Machine Learning from two main perspectives: Scientific and Practical. We provide the necessary scientific knowledge for each ML concept while avoiding unnecessary details. This approach helps learners understand how to use, implement, and develop ML models accurately, minimizing time spent on trial and error.The second perspective is practical, allowing learners to both implement ML models from scratch to deeply understand their operation and use pre-built ML models from packages such as Scikit-learn.These perspectives ensure learners become well-versed ML engineers, DL Engineers, data scientists, and AI engineers.This is the first course in the series: Introduction to Machine Learning.This is not just like any introduction to ML you may saw; it is a comprehensive and detailed one, which is why it is offered as a separate course.In this comprehensive introduction, you will learn the following:1. What is the AI?2. The difference between AI and Data Science (DS)?3. What is Soft Computing (SC)?4. What exactly is ML?5. Why we need ML?6. What is the Deep Learning (DL)?7. ML Applications.8. ML types: Based on amount of Supervision. 8.1. Supervised learning. 8.1.1 Regression. 8.1.2 Classification. 8.2 Unsupervised learning. 8.2.1 Clustering. 8.2.2 Anomaly detection. 8.2.3 Dimensionality reduction. 8.2.4Association rule. 8.3 Semi-supervised learning. 8.4 Self-supervised learning. 8.5 Reinforcement learning.9. ML types: Based on whether or not the system can learn incrementally from a stream of incoming data. 9.1 Batch learning. 9.2 Incremental learning.10. ML types: Based on how they generalize. 10.1 Instance based learning. 10.2 Model based learning.11. Python Example of: 11.1 Applying model based learning to solve LINEAR REGRESSION problem 11.2 Applying instance based learning to solve LINEAR REGRESSION problem. 11.3 Applying model based learning to solve CLASSIFICATION problem 11.4 Applying instance based learning to solve CLASSIFICATION problem.
