|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/practical-machine-learning/
课程评论：没有评论
Coursera 课程《Python 机器学习实用入门》课程总结 **课程概述：** LinkedIn 最新发布的“新兴职业”榜单显示，人工智能专家——即与机器学习相关的职位，是增长最快的职业类别，招聘需求在过去几年中增长了 74%。机器学习是自动驾驶汽车、智能音箱、推荐系统和复杂预测等技术的驱动力，是一个充满机遇且快速发展的激动人心的领域。许多组织目前都面临机器学习人才短缺的问题。 本课程面向广泛的初学者，旨在帮助学员理解机器学习的优势、工作原理以及后续的学习路径。课程将通过真实的机器学习应用案例进行演示，所有代码示例均可在 GitHub 上获取，并支持在 Google Colab 中运行。Google Colab 是一个免费的云端机器学习和数据科学平台，提供 GPU 支持以缩短模型训练时间，用户只需使用现代网页浏览器即可，无需任何软件安装。 **主要更新和亮点：** * **2019 年 7 月更新：** 增加了关于自监督学习的讲座和示例。自监督学习是一种令人兴奋的技术，它使机器能够从无需昂贵人工标注的数据中学习，通过预测数据集中缺失或后续的内容来实现。这种学习方式部分受到早期儿童学习的启发，并能产生令人印象深刻的结果。学员将有机会亲身体验自监督学习，深入了解其工作原理和解决问题的能力。 * **2019 年 8 月更新：** 提供了使用两种不同方法将数据加载到 Google Colab 的分步演示。Google Colab 是一个强大的机器学习环境，提供免费 GPU 支持，允许用户加载自己的数据进行训练和测试。 * **2020 年 3 月更新：** 将所有示例迁移到 Google Colab，并更新至 TensorFlow 2。TensorFlow 2 是目前最流行的机器学习框架之一，用户无需安装任何软件。 * **2020 年 4 月/5 月更新：** 优化了课程内容，并增加了 Jupyter Notebook 讲座和作业。Jupyter Notebook 是机器学习开发的首选环境。 **目标群体：** * 希望了解机器学习是什么以及它是如何工作的初学者。 * 有意从零开始开发机器学习模型的软件开发者（可考虑进阶课程《Python 机器学习实例实战》）。 **学习成果：** 完成本课程后，学员将能够理解机器学习的益处，掌握其基本工作原理，并了解下一步的学习方向。
LinkedIn released it's annual "Emerging Jobs" list, which ranks the fastest growing job categories. The top role is Artificial Intelligence Specialist, which is any role related to machine learning. Hiring for this role has grown 74% in the past few years!Machine learning is the technology behind self driving cars, smart speakers, recommendations, and sophisticated predictions. Machine learning is an exciting and rapidly growing field full of opportunities. In fact, most organizations can not find enough AI and ML talent today.If you want to learn what machine learning is and how it works, then this course is for you. This course is targeted at a broad audience at an introductory level. By the end of this course you will understand the benefits of machine learning, how it works, and what you need to do next. If you are a software developer interested in developing machine learning models from the ground up, then my second course, Practical Machine Learning by Example in Python might be a better fit.There are a number of machine learning examples demonstrated throughout the course. Code examples are available on github. You can run each examples using Google Colab. Colab is a free, cloud-based machine learning and data science platform that includes GPU support to reduce model training time. All you need is a modern web browser, there's no software installation is required! July 2019 course updates include lectures and examples of self-supervised learning. Self-supervised learning is an exciting technique where machines learn from data without the need for expensive human labels. It works by predicting what happens next or what's missing in a data set. Self-supervised learning is partly inspired by early childhood learning and yields impressive results. You will have an opportunity to experiment with self-supervised learning to fully understand how it works and the problems it can solve.August 2019 course updates include a step by step demo of how to load data into Google Colab using two different methods. Google Colab is a powerful machine learning environment with free GPU support. You can load your own data into Colab for training and testing.March 2020 course updates migrate all examples to Google Colab and Tensorflow 2. Tensorflow 2 is one of the most popular machine learning frameworks used today. No software installation is required.April/May 2020 course updates streamline content, include Jupyter notebook lectures and assignment. Jupyter notebook is the preferred environment for machine learning development.
