Fundamentals of Machine Learning

位教师：Whizlabs Instructor

访问权限由 New York State Department of Labor 提供

6个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

6个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

您将获得的技能

Microsoft Azure
Deep Learning
Data Preprocessing
Model Deployment
Unsupervised Learning
Supervised Learning
MLOps (Machine Learning Operations)
Amazon Web Services
AWS SageMaker
Azure DevOps
Machine Learning
Applied Machine Learning
Cloud Computing
Data Processing
Artificial Intelligence and Machine Learning (AI/ML)
Model Evaluation
技能部分已折叠。显示 9 项技能，共 16 项。

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

12 项作业

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

该课程共有6个模块

This course provides a comprehensive introduction to the Fundamentals of Machine Learning, covering both conceptual understanding and practical implementation across modern machine learning workflows. It focuses on building strong core foundations, preparing and evaluating data, applying supervised and unsupervised learning techniques, and implementing scalable machine learning solutions using cloud platforms such as AWS and Azure.

Participants will gain hands-on experience in developing, training, evaluating, and optimizing machine learning models, along with exposure to advanced techniques such as GPU-accelerated workflows and MLOps. Real-world use cases, demos, and step-by-step guidance are included to ensure learners can confidently apply machine learning concepts in practical scenarios. By the end of this course, you will be able to learn how to: Understand and explain core machine learning concepts, terminology, and workflows Differentiate between AI, Machine Learning, and Deep Learning Prepare, preprocess, and evaluate data for machine learning models Build and evaluate supervised learning models for classification and regression problems Apply unsupervised learning techniques for clustering and pattern discovery Optimize models using cross-validation, hyperparameter tuning, and performance metrics Leverage GPU-accelerated workflows for large-scale machine learning tasks Design and implement machine learning solutions on AWS Build, manage, and operationalize ML workflows using Azure Machine Learning and MLOps best practices This course facilitates learners with approximately 6:30–7:00 hours of video lectures, delivering a balanced mix of theory and hands-on demonstrations. The course is divided into 6 modules, and each module is further split into focused lessons. To reinforce learning, each module includes assignments in the form of quizzes and in-video questions. Course Modules Module 1: Building Core Concepts and Foundations of Machine Learning Module 2: ML Development, Data Preparation, and Evaluation Module 3: Unsupervised Learning Techniques – Clustering and Pattern Discovery Module 4: Advanced Machine Learning Techniques and GPU-Accelerated Workflows Module 5: Designing and Implementing Machine Learning Solutions on AWS Module 6: Building & Managing ML Workflows with Azure Machine Learning and MLOps This course is ideal for learners and professionals who want to build a strong foundation in machine learning and progress toward real-world, cloud-based ML implementations using industry-standard tools and best practices.

Welcome to Week 1 of the Fundamentals of Machine Learning course. In this week, you will be introduced to the core concepts of machine learning and set clear expectations for what you’ll learn throughout the course. We’ll begin by understanding what machine learning is and how it differs from artificial intelligence and deep learning. You’ll explore the major types of machine learning and gain a foundational understanding of supervised learning, including classification and regression techniques. We’ll also walk through the end-to-end steps involved in building a machine learning solution. By the end of this week, you will have a strong conceptual foundation in machine learning, enabling you to understand key terminology, learning paradigms, and the overall ML lifecycle.

涵盖的内容

7个视频2篇阅读材料2个作业1个讨论话题

7个视频总计39分钟

What is Machine Learning ? 5分钟
Expectations from Fundamentals of Machine Learning 2分钟
Al Vs Deep Learning Vs Machine Learning 3分钟
Types of Machine Learning 5分钟
Supervised Machine Learning - Classification 8分钟
Supervised Machine Learning - Regression 8分钟
Steps for Machine Learning 9分钟

2篇阅读材料总计60分钟

Welcome to the Course 30分钟
Overview of Building Core Concepts and Foundations of ML 30分钟

2个作业总计65分钟

Building Core Concepts and Foundations of ML - Assessment 30分钟
Core Principles of Machine Learning - Knowledge Check 35分钟

1个讨论话题总计10分钟

Meet and Greet 10分钟

Welcome to Week 2. This week focuses on the practical aspects of building and evaluating machine learning models. You will learn how to prepare data through preprocessing techniques, select and train appropriate models, and evaluate their performance using standard metrics. Through hands-on demos, you will explore classification tasks, understand confusion matrices, and apply evaluation metrics for both classification and regression models. By the end of the week, you will be able to assess model performance effectively and make informed decisions during the model training and evaluation process.

涵盖的内容

8个视频1篇阅读材料2个作业

8个视频总计61分钟

Classification task - Demo 11分钟
Model Selection, Training and Evaluation 7分钟
Data Preprocessing Essentials 7分钟
Data Preprocessing - Demo 11分钟
Evaluating Classification Models 5分钟
Confusion Matrix 5分钟
Evaluation Metrics - Regression 7分钟
Evaluation Metrics - Demo 9分钟

1篇阅读材料总计30分钟

Overview of ML Development, Data Preparation, and Evaluation 30分钟

2个作业总计80分钟

ML Development, Data Preparation, and Evaluation - Assessment 40分钟
End-to-End Machine Learning Model Building - Knowledge Check 40分钟

Welcome to Week 3. This week, we will dive into unsupervised machine learning techniques used to uncover hidden patterns and structures in data. You will learn the fundamentals of clustering, including K-Means, hierarchical clustering, and density-based clustering, along with hands-on demonstrations. We will also explore association rule mining to understand relationships within datasets. By the end of the week, you will be able to apply unsupervised learning methods to discover insights without labeled data.

涵盖的内容

5个视频1篇阅读材料2个作业

5个视频总计33分钟

Unsupervised Learning - Clustering 6分钟
Understanding KMeans Clustering 5分钟
Clustering - Demo 10分钟
Hierarchial Clustering and Density-Based Clustering 6分钟
Unsupervised Learning - Association Rule Mining 6分钟

1篇阅读材料总计30分钟

Overview of Unsupervised Learning Techniques: Clustering and Pattern Discovery 30分钟

2个作业总计60分钟

Unsupervised Learning Techniques: Clustering and Pattern Discovery - Assessment 30分钟
Discovering Patterns with Unsupervised Learning - Knowledge Check 30分钟

Welcome to Week 4. In this week, we will focus on advanced machine learning techniques and performance optimization. You will be introduced to NVIDIA RAPIDS and learn how GPUs can significantly accelerate data processing and machine learning workflows through hands-on demonstrations. We will explore model optimization techniques such as cross-validation using GridSearch and RandomizedSearch to improve model performance and reliability. Finally, you will learn the fundamentals of time series analysis using the ARIMA model and implement it through practical demos. By the end of the week, you will be able to optimize ML workflows, select well-tuned models, and apply time-series techniques to real-world forecasting problems.

涵盖的内容

6个视频1篇阅读材料2个作业

6个视频总计43分钟

Introduction to Nvidia RAPIDS 5分钟
Accelerating the ML Workflow on GPU - Demo 6分钟
Cross Validation Techniques - GridSearch & RandomizedSearch 6分钟
Cross Validation Techniques - Demo 12分钟
ARIMA Model - Time Series Analysis 7分钟
ARIMA Model - Demo 9分钟

1篇阅读材料总计30分钟

Overview of Advanced ML Techniques and GPU-Accelerated Workflows 30分钟

2个作业总计70分钟

Advanced ML Techniques and GPU-Accelerated Workflows- Assessment 35分钟
Scaling Machine Learning with Advanced Techniques - Knowlegde check 35分钟

Welcome to Week 5. This week focuses on applying machine learning in real-world scenarios. You will learn how to identify suitable machine learning use cases, understand the differences between AI, machine learning, and deep learning, and explore AWS services that support ML workloads. We will also cover how ML and deep learning models are used in production, including serving data for model training and designing effective data ingestion strategies. By the end of the week, you will be able to align ML solutions with business needs and design practical, production-ready ML workflows.

涵盖的内容

4个视频1篇阅读材料2个作业

4个视频总计22分钟

Example Use Cases to Identify the Machine Learing Use Case 8分钟
AWS Services for Machine Learning 6分钟
Usage of Deep Learning/ ML models in Production 5分钟
Understanding difference - AI Vs Deep Learning Vs Machine Learning 3分钟

1篇阅读材料总计30分钟

Overview of Designing and Implementing Machine Learning Solutions on AWS 30分钟

2个作业总计50分钟

Designing and Implementing Machine Learning Solutions on AWS - Assessment 25分钟
Operationalizing Machine Learning on AWS - Knowledge check 25分钟

Welcome to Week 6. This week focuses on building and operationalizing machine learning solutions using Azure Machine Learning and MLOps practices. You will learn how to organize and manage Azure Machine Learning environments, understand the role of the Azure Machine Learning workspace, and explore the end-to-end workflow involved in developing, training, and deploying machine learning models. The week also introduces core machine learning concepts, including different types of machine learning tasks, commonly used algorithms, and the use of AutoML to simplify model selection and optimization. By the end of the week, you will be able to design an effective MLOps architecture and implement structured, scalable, and production-ready machine learning workflows using Azure Machine Learning.