AI and Machine Learning Algorithms and Techniques

本课程是 Microsoft AI & ML Engineering 专业证书的一部分

位教师： Microsoft

访问权限由 New York State Department of Labor 提供

11,072 人已注册

5个模块

深入了解一个主题并学习基础知识。

63 条评论

中级等级

推荐体验

灵活的计划

5 周在 10 小时一周

自行安排学习进度

98%

大多数学生喜欢此课程

5个模块

深入了解一个主题并学习基础知识。

63 条评论

中级等级

推荐体验

灵活的计划

5 周在 10 小时一周

自行安排学习进度

98%

大多数学生喜欢此课程

您将获得的技能

您将学习的工具

Generative AI

要了解的详细信息

可分享的证书

添加到您的领英档案

作业

45 任务¹

AI 评分请参见免责声明

授课语言：英语（English）

了解顶级公司的员工如何掌握热门技能

了解关于 Coursera for Business 的更多信息

Petrobras, TATA, Danone, Capgemini, P&G 和 L'Oreal 的徽标

积累 Software Development 领域的专业知识

本课程是 Microsoft AI & ML Engineering 专业证书专项课程的一部分

在注册此课程时，您还会同时注册此专业证书。

向行业专家学习新概念
获得对主题或工具的基础理解
通过实践项目培养工作相关技能
通过 Microsoft 获得可共享的职业证书

该课程共有5个模块

This course covers the core algorithms and techniques used in AI and ML, including approaches that use pre-trained large-language models (LLMs). You will explore supervised, unsupervised, and reinforcement learning paradigms, as well as deep learning approaches, including how these operate in pre-trained LLMs. The course emphasizes the practical application of these techniques and their strengths and limitations in solving different types of business problems.

By the end of this course, you will be able to: 1. Implement, evaluate, and explain supervised, unsupervised, and reinforcement learning algorithms. 2. Apply feature selection and engineering techniques to improve model performance. 3. Describe deep learning models for complex AI tasks. 4. Assess the suitability of various AI & ML techniques for specific business problems. To be successful in this course, you should have intermediate programming knowledge of Python, plus basic knowledge of AI and ML capabilities, and newer capabilities through generative AI (GenAI) and pretrained large language models (LLM). Familiarity with statistics is also recommended.

In this module, you'll embark on a comprehensive journey through the essentials of supervised ML. This module is designed to equip you with a robust understanding and practical skills in the field, ensuring you're well prepared to tackle real-world data problems. By the end of this module, you'll not only have a strong theoretical foundation but also practical experience in supervised learning, enabling you to confidently develop, evaluate, and optimize predictive models for a variety of applications.

涵盖的内容

9个视频30篇阅读材料15个作业

9个视频总计45分钟

Introduction to the AI/ML engineering advanced professional certificate program 4分钟
Introduction to the AI/ML algorithms and techniques course 5分钟
The importance of algorithms and techniques in your work 8分钟
What is supervised learning? 7分钟
Compare implementation techniques using Python 5分钟
Use case demonstration of evaluation metrics 5分钟
Use case demonstration of cross-validation and multiple metrics in ML 4分钟
Walkthrough: Use cases of feature selection techniques in live demonstrations (Optional) 4分钟
Summary: Supervised learning 5分钟

30篇阅读材料总计576分钟

Welcome to the Coursera Community 2分钟
Microsoft updates 2分钟
Practice activity: Setting up your environment in Microsoft Azure 30分钟
Walkthrough: Setting up your environment in Microsoft Azure (Optional) 0分钟
Practice activity: Creating your own code repository using Git 45分钟
Walkthrough: Creating your own code repository using Git (Optional) 0分钟
Course syllabus: AI and Machine Learning Algorithms and Techniques 10分钟
Key principles and approaches to supervised learning 10分钟
Best practices for implementing supervised learning algorithms 10分钟
Practice activity: Integrating linear regression 30分钟
Walkthrough: Integrating linear regression (Optional) 0分钟
Practice activity: Implementing logistic regression 30分钟
Walkthrough: Implementing logistic regression (Optional) 0分钟
Practice activity: Implementing decision trees 30分钟
Walkthrough: Implementing decision trees (Optional) 0分钟
Practice activity: Implementing and comparing models 75分钟
Walkthrough: Implementing and comparing models (Optional) 0分钟
Evaluation metrics for supervised learning models 12分钟
Practice activity: Applying metrics and cross-validation 90分钟
Walkthrough: Applying metrics and cross-validation (Optional) 0分钟
Feature selection methods: Backward elimination, forward selection, and LASSO 5分钟
Practice activity: Implementing backward elimination 40分钟
Walkthrough: Implementing backward elimination (Optional) 0分钟
Practice activity: Implementing forward selection 40分钟
Walkthrough: Implementing forward selection (Optional) 0分钟
Practice activity: Implementing LASSO 45分钟
Walkthrough: Implementing LASSO (Optional) 0分钟
Practice activity: Implementing feature selection techniques on a given dataset 60分钟
Walkthrough: Implementing feature selection techniques on a given dataset (Optional) 0分钟
Industry exemplar: Feature selection techniques 10分钟

15个作业总计93分钟

Knowledge check: Algorithms and techniques 10分钟
Reflection: Setting up your environment in Microsoft Azure 3分钟
Reflection: Creating your own code repository 3分钟
Knowledge check: Supervised learning 10分钟
Reflection: Integrating linear regression 3分钟
Reflection: Implementing logistic regression 3分钟
Reflection: Implementing decision trees 3分钟
Reflection: Implementing and comparing models 3分钟
Reflection: Applying metrics and cross-validation 3分钟
Knowledge check: Cross-validation and multiple metrics 10分钟
Reflection: Implementing backward elimination 3分钟
Reflection: Implementing forward selection 3分钟
Reflection: Implementing LASSO 3分钟
Reflection: Implementing feature selection techniques on a given dataset 3分钟
Graded quiz: Feature selection techniques 30分钟

This module is a deep dive into the world of data analysis where the patterns and insights are uncovered without predefined labels. It is tailored to provide a comprehensive understanding and practical skills in unsupervised learning, empowering you to discover hidden structures within your data. By the end of this module, you'll have a solid grasp of unsupervised learning concepts and practical skills in implementing, analyzing, and comparing different algorithms. This knowledge will enable you to unlock valuable insights from complex datasets and make informed decisions based on your analyses.

涵盖的内容

4个视频18篇阅读材料9个作业

4个视频总计19分钟

Overview of unsupervised learning 3分钟
How to implement and visualize clustering 5分钟
Use case demonstration of dimensionality reduction 5分钟
Walkthrough: Implementing unsupervised learning methods (Optional) 6分钟

18篇阅读材料总计355分钟

Key principles and approaches to unsupervised learning 10分钟
Introduction to clustering techniques 10分钟
Practice activity: Implementing k-means clustering 40分钟
Walkthrough: Implementing k-means clustering (Optional) 0分钟
Practice activity: Implementing DBSCAN clustering 30分钟
Walkthrough: Implementing DBSCAN clustering (Optional) 0分钟
Practice activity: Implementing clustering and visualization 45分钟
Walkthrough: Clustering and visualization (Optional) 0分钟
Dimensionality reduction techniques 10分钟
Practice activity: Implementing dimensionality reduction techniques 60分钟
Walkthrough: Implementing dimensionality reduction techniques (Optional) 0分钟
Comparing unsupervised learning approaches for different datasets 10分钟
Practice activity: Interpreting clustering and dimensionality reduction outcomes 45分钟
Walkthrough: Interpreting clustering and dimensionality reduction outcomes (Optional) 0分钟
Discussion: Comparing unsupervised learning approaches for different datasets 30分钟
Summary: Unsupervised learning 10分钟
Practice activity: Implementing unsupervised learning methods 50分钟
Industry exemplar: Application of unsupervised learning techniques 5分钟

9个作业总计78分钟

Knowledge check: Unsupervised learning principles 15分钟
Reflection: Implementing k-means clustering 3分钟
Reflection: Implementing DBSCAN clustering 3分钟
Reflection: Implementing clustering and visualization 3分钟
Reflection: Implementing dimensionality reduction techniques 3分钟
Knowledge check: Dimensionality reduction 15分钟
Reflection: Interpreting clustering and dimensionality reduction outcomes 3分钟
Reflection: Implementing unsupervised learning methods 3分钟
Graded quiz: Unsupervised learning 30分钟

This module is designed to provide an in-depth exploration of cutting-edge techniques in ML. This module merges foundational reinforcement learning concepts with advanced strategies for enhancing language generation models, offering a well-rounded understanding of these pivotal areas in AI. By the end of this module, you’ll be equipped with theoretical knowledge and practical experience in reinforcement learning and language model enhancement. This comprehensive understanding will enable you to tackle complex problems and contribute to innovative solutions in the rapidly evolving field of AI.

涵盖的内容

6个视频11篇阅读材料6个作业

6个视频总计33分钟

Overview of reinforcement learning 5分钟
Comparing implementation techniques using Python 6分钟
Use case demonstration for applying model evaluation metrics 7分钟
Summary of reinforcement learning and other approaches 5分钟
Walkthrough: Reinforcement learning and other approaches (Optional) 5分钟
Industry exemplar: Reinforcement learning and other approaches 5分钟

11篇阅读材料总计375分钟

Key principles and approaches of reinforcement learning 20分钟
Practice activity: Comparing and reinforcing learning algorithms 90分钟
Walkthrough: Comparing Q-learning and policy gradients (Optional) 0分钟
Evaluation metrics for reinforcement learning models 15分钟
Practice activity: Applying model evaluation metrics in reinforcement learning 90分钟
Walkthrough: Applying model evaluation metrics (Optional) 0分钟
Comparing reinforcement learning with supervised and unsupervised learning 10分钟
Use case demonstration for supervised, unsupervised, and reinforcement learning 20分钟
Discussion: Comparative analysis of learning paradigms 30分钟
Use case comparison of supervised, unsupervised, and reinforcement learning 10分钟
Practice activity: Implementing reinforcement learning and other approaches 90分钟

6个作业总计69分钟

Knowledge check: Reinforcement learning principles 15分钟
Reflection: Q-Learning and Policy Gradients 3分钟
Reflection: Model evaluation metrics 3分钟
Knowledge check: Evaluation metrics for performance models 15分钟
Reflection: Implemented supervised learning, unsupervised learning, and reinforcement learning approaches 3分钟
Graded quiz: Reinforcement learning and other approaches 30分钟

This module is designed to provide a comprehensive introduction to neural networks and their applications in modern AI. It will guide you through the core principles of deep learning, from basic neural network architecture to advanced applications in image and text data, while also exploring the significance of deep learning within the realm of generative AI (GenAI). By the end of this module, you will have a solid grasp of neural network architectures, practical experience with deep learning techniques, and a clear understanding of how these technologies are applied within the broader landscape of GenAI. This knowledge will enable you to leverage deep learning effectively in academic and real-world scenarios.

涵盖的内容

5个视频14篇阅读材料8个作业

5个视频总计32分钟

Overview of neural networks 5分钟
Walkthrough: Implementing and comparing neural network architectures in TensorFlow and PyTorch (Optional) 9分钟
Use case demonstration of FNNs, CNNs, and RNNs 5分钟
Walkthrough: Analyzing a dataset and implementing a neural network for deep learning analysis (Optional) 6分钟
Hear from an expert: Industry exemplar of deep learning and neural networks 7分钟

14篇阅读材料总计485分钟

Key features and architectures of neural networks 10分钟
Implementing neural networks in Azure 15分钟
Comparing neural network implementation techniques using Python 15分钟
Practice activity: Implementing a neural network with TensorFlow 75分钟
Walkthrough: Implementing a neural network with TensorFlow (Optional) 0分钟
Practice activity: Implementing and comparing neural network architectures 90分钟
Explanation of deep learning techniques 15分钟
Practice activity: Implementing deep learning techniques 90分钟
Walkthrough: Implementing deep learning techniques (FNN, CNN, RNN) (Optional) 0分钟
Implementation of deep learning techniques: GANs and autoencoders 15分钟
Practice activity: Evaluating deep learning models in the context of generative AI 105分钟
Walkthrough: Evaluating deep learning models in the context of generative AI (Optional) 0分钟
Summary: Deep learning and neural networks 10分钟
Practice activity: Analyzing a dataset and implementing a neural network for deep learning analysis 45分钟

8个作业总计75分钟

Knowledge check: Key architectures and features of neural networks 15分钟
Reflection: Implementing a neural network with TensorFlow 3分钟
Reflection: Implementing and comparing neural network architectures 3分钟
Reflection: Implementing deep learning techniques 3分钟
Knowledge check: Deep learning techniques 15分钟
Reflection: Evaluating deep learning models in the context of generative AI 3分钟
Reflection: Analyzing a dataset and implementing a neural network for deep learning analysis 3分钟
Graded quiz: Deep learning and neural networks 30分钟

This module is a focused exploration of the roles, responsibilities, and approaches in the field of AI and ML within a business environment. It is designed to provide a comprehensive understanding of how AI/ML engineers operate, the distinctions between handling in-house developed models versus pretrained models and how they collaborate with other key roles in the corporate ecosystem. By the end of this module, you will have a clear understanding of the various approaches to AI/ML engineering, the specific responsibilities associated with different types of models, and the collaborative dynamics within a corporate setting. This knowledge will empower you to navigate and contribute effectively to AI/ML projects in a business environment.

涵盖的内容

7个视频16篇阅读材料7个作业1次同伴评审

7个视频总计33分钟

Overview of AI/ML engineering approaches 6分钟
Hear from an expert: Aligning AI with organizational goals 4分钟
The Importance of collaboration in AI/ML professions 4分钟
Hear from an expert: Balancing business and technical priorities 7分钟
Summary: AI/ML engineering and working with models 6分钟
Summary, thank you, and good luck 3分钟
Thank you, and congratulations! 2分钟

16篇阅读材料总计355分钟

Real-world case studies of corporate AI/ML implementations 10分钟
Practice activity: Implementing a corporate approach in context 30分钟
Practice activity: Deploying and repairing AI/ML systems 30分钟
Walkthrough: Deploying and repairing AI/ML systems (Optional) 0分钟
The roles of AI/ML engineers 10分钟
Detailed role descriptions of AI/ML engineers in industry 10分钟
Discussion: Comparing AI/ML engineer roles 30分钟
Considering your career in AI/ML engineering 10分钟
Practice activity: Identifying your strengths, weaknesses, and interests in AI/ML engineering 30分钟
Understanding team dynamics in AI/ML development teams 10分钟
Comprehensive guide 5分钟
Tools and platforms for further learning 5分钟
Industry exemplar: Discussing roles in AI/ML 10分钟
Practice activity: Creating an AI/ML development plan for a fictitious project 45分钟
Walkthrough: Creating an AI/ML development plan for customer churn prediction (Optional) 0分钟
Practice activity: Designing and developing an AI/ML solution 120分钟

7个作业总计72分钟

Reflection: Deploying and repairing AI/ML systems 3分钟
Knowledge check: AI/ML engineering approaches 15分钟
Knowledge check: Matching AI/ML engineering roles to responsibilities 15分钟
Reflection: Identifying your strengths, weaknesses, and interests in AI/ML engineering 3分钟
Reflection: Creating an AI/ML development plan for a fictitious project 3分钟
Knowledge check: Designing and developing an AI/ML solution 3分钟
Graded quiz: AI/ML engineering and working with models 30分钟