Machine Learning

Machine Learning

位教师：Dr. Mohit Bhatnagar

访问权限由 New York State Department of Labor 提供

2,618 人已注册

11个模块

深入了解一个主题并学习基础知识。

初级等级

推荐体验

4 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

11个模块

深入了解一个主题并学习基础知识。

初级等级

推荐体验

4 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

您将学到什么

Learn to frame real-world challenges as machine learning problems. Gain hands-on experience using Python to build and evaluate models.

您将获得的技能

您将学习的工具

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

16 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11个模块

This Course Machine Learning offers a comprehensive, hands-on introduction to building and deploying machine learning models using Python. It is designed for learners with a foundational understanding of Python programming and familiarity with basic data analysis concepts. The course begins with a quick review of essential Python libraries such as NumPy, pandas, and Matplotlib, which form the foundation for data manipulation and visualization in data science.

Learners are then introduced to core machine learning concepts, including supervised learning techniques such as classification and regression. The course places a strong emphasis on practical implementation using the scikit-learn package, enabling learners to build, train, and evaluate various models effectively. It also covers artificial neural networks and delves into deep learning through TensorFlow, where participants apply regression and classification techniques on real-world datasets. With the growing importance of unstructured data, the course explores neural network-based models for analyzing text and image data, equipping learners to handle diverse data types. By the end of the course, participants will have the ability to design and implement machine learning workflows, drawing actionable business insights from both structured and unstructured data. This skill set supports careers in data analysis, data engineering, and data science across industries.

Welcome to the Machine Learning course! In this course, you will gain an in-depth introduction to building machine-learning models using Python. In this course, you will initially recapitulate the key Python libraries which are useful for Data Science applications. This includes coverage of Python libraries like Matplotlib, NumPy, and pandas. Next, you are introduced to the basics of machine learning, and the various classification and regression techniques are discussed. Also, the implementation of these techniques using the popular scikit-learn package is covered in detail. Artificial neural networks and the concept of deep learning is next explored with hands-on implementation of regression and classification algorithms using TensorFlow. As businesses increasingly draw insights from unstructured data (text, images, etc.), you would also get insights into neural networks-based deep learning models for the analysis of text and images. This is an advanced-level course, intended for learners with a background using predictive tools and techniques, and a basic understanding of Python programming concepts. The knowledge you gain from this course will help your career as a business analyst or a data engineer and even work toward becoming a data scientist. You will gain skills to apply machine learning algorithms to structured and unstructured data to draw management insights. Data science is an exciting new field used by various organizations to perform data-driven decisions. It is a combination of technical knowledge, mathematics, and business. In this module, we will use Python, one of the most popular languages among all the languages used by data scientists. We will also understand various topics of data science and how to apply them in a real-world scenario.

涵盖的内容

9个视频5篇阅读材料2个作业1个讨论话题

9个视频总计33分钟

Course Introduction 3分钟
Working with Google Colab 5分钟
Python Basics: Basic Data Structures and Functions 5分钟
Plotting Libraries for Python: Matplotlib 4分钟
Plotting Libraries for Python: Seaborn 3分钟
Working with Arrays: NumPy - Part 1 5分钟
Working with Arrays: NumPy - Part 2 3分钟
Python Data Frames: pandas - Part 1 3分钟
Python Data Frames: pandas - Part 2 3分钟

5篇阅读材料总计180分钟

Essential Reading: Getting Started with Google Colaboratory 15分钟
Essential Reading: Learn Python in 7 Days: Learn Efficient Python Coding Within 7 Days 60分钟
Essential Reading: Visualization of Data 15分钟
Essential Reading: Numerical Computing with NumPy 45分钟
Essential Reading: Data Manipulation and Analysis with pandas 45分钟

2个作业总计30分钟

Python Basics 15分钟
Python for Data Science 15分钟

1个讨论话题总计20分钟

Applications of NumPy and pandas in Business Problems 20分钟

This assessment is a graded quiz based on the modules covered this week.

涵盖的内容

1个作业

In this module, you will learn about the origin and evolution of machine learning. You will also learn the different ways a machine can learn, and the essential components needed to develop a machine-learning model. You will get an overview of different types of algorithms that you can use to train machine-learning models for specific business problems. The nature and type of data needed to train these algorithms will also be discussed. The module also discusses the different real-world and business best practices and challenges one will have to be sensitive to while deploying machine learning to support business operations.

涵盖的内容

9个视频2篇阅读材料2个作业

9个视频总计67分钟

History and Evolution of Machine Learning 7分钟
How a Machine Learns? 9分钟
Types of Machine Learning 6分钟
Best-Practices for Using Machine Learning in Business 6分钟
ML Algorithms for Classification Part 1: Decision Tree and KNN 9分钟
ML Algorithms for Classification Part 2: Naive-Bayes 8分钟
ML Algorithms for Prediction (Regression) 7分钟
Clustering Using ML: k-means Clustering 7分钟
Understanding the Bias-Variance Trade-Off 7分钟

2篇阅读材料总计240分钟

Essential Reading: Origins and Development of Machine Learning 120分钟
Essential Reading: Machine Learning in Business 120分钟

2个作业总计30分钟

Origins of Machine Learning 12分钟
Machine Learning in Business 18分钟

In this module, you will re-examine several machine learning models. We will discuss hands-on tasks that machine learning is commonly applied to, and you will learn to measure the performance of machine learning systems. We will work with a popular library for the Python programming language called scikit-learn, which has assembled state-of-the-art implementations of many machine learning algorithms.

涵盖的内容

9个视频4篇阅读材料2个作业1个讨论话题

9个视频总计33分钟

Introduction to Sklearn 4分钟
Pre-Processing Tasks: Dimensionality Reduction, Normalization, and Train Test Split 5分钟
Implementation of a Linear Regression Model 3分钟
Evaluation of the Regression Model and Making Predictions 3分钟
Stepwise Regression and Regularization for Model Simplification 4分钟
Implementation of a Logistic Regression Model 3分钟
Evaluation of Classification Models: AUC, Recall, and Precision 4分钟
Evaluating Other Classifiers for Model Improvement 3分钟
Clustering Using Sklearn 3分钟

4篇阅读材料总计285分钟

Essential Reading: Getting Started with Scikit-learn 15分钟
Essential Reading: Machine Learning with Scikit-learn Quick Start 90分钟
Essential Reading: Machine Learning with Scikit-Learn 90分钟
Recommended Reading: Machine Learning by Examples 90分钟

2个作业总计30分钟

Introduction to Machine Learning Using Python 15分钟
Classification and Clustering Using Python 15分钟

1个讨论话题总计20分钟

Applications of Simple Linear and Multiple Linear Regression 20分钟

This assessment is a graded quiz based on the modules covered this week.

涵盖的内容

1个作业

In this module, you will learn about artificial neural networks (ANNs) and their role in machine learning. You will also learn about the perceptron, the first real-world application based on neural networks. The concepts of weights, biases, and activation functions along with their role in analyzing data and training of ANNs will be discussed. We will also discuss how concepts like backpropagation and gradient descent affect the process of learning with ANNs.

涵盖的内容

6个视频2篇阅读材料2个作业

6个视频总计47分钟

Origins of ANN and the Perceptron 7分钟
Using ANNs to Solve Business Use-Cases 8分钟
Learning with a Perceptron 8分钟
Activation Functions 8分钟
Cost Function and Gradient Descent 10分钟
Challenges in Using ANNs 7分钟

2篇阅读材料总计240分钟

Essential Reading: Introduction of Artificial Neural Network (ANN) 120分钟
Essential Reading: ANNs and Their Issues 120分钟

2个作业总计30分钟

Introduction of Artificial Neural Network (ANN) 18分钟
ANNs and Their Issues 12分钟

In this module, you will learn about using neural network technique for predictive tasks. You will also learn how to use the Python open source TensorFlow machine learning library for implementing regression and classification models to draw insights from structured and unstructured text data. The module also discusses methods for hyperparameter tuning for performance improvement. Lastly, this module will help you to define deep learning models and look at the problem of overfitting and look at ways to identify and overcome it.

涵盖的内容

11个视频4篇阅读材料2个作业1个讨论话题

11个视频总计54分钟

Recap of the Artificial Neural Network 5分钟
Design decisions for an ANN 5分钟
Introduction to TensorFlow 7分钟
Defining a Regression Model for Prediction 6分钟
Hyperparameter Tuning for Performance Improvement 5分钟
Saving Models and Using them in Production 2分钟
Revisiting the Bag of Words Model 7分钟
Implementing a Sentiment Analysis Application 6分钟
TensorFlow model for Classification 4分钟
Identifying Overfitting and Overcoming It 5分钟
Performance Evaluation of a Classification Model 4分钟

4篇阅读材料总计240分钟

Essential Reading: Deep Learning with Python and TensorFlow 60分钟
Recommended Reading: TensorFlow Tutorials 60分钟
Essential Reading: Deep Learning with Python and TensorFlow 60分钟
Recommended Reading: TensorFlow Tutorials 60分钟

2个作业总计30分钟

Regression Modeling Using TensorFlow 15分钟
Implementing a Sentiment Classifier 15分钟

1个讨论话题总计20分钟

Classification Versus Regression 20分钟

This assessment is a graded quiz based on the module covered this week.

涵盖的内容

1个作业

In this module, you will be introduced to the concept of word and image embeddings which are transforming natural language and image processing applications. You will learn how to generate word embeddings using a corpus of text and also use pre trained word embeddings like Glove and Fasttext. This module will also discuss convolution neural networks and image vector-based models for image classification tasks.

涵盖的内容

11个视频4篇阅读材料2个作业1个讨论话题

11个视频总计61分钟

Natural Language Processing: An Overview 5分钟
Introduction to the Concept of Word Embeddings  5分钟
Generating Word Embeddings 7分钟
Hands-On with Word Embeddings 10分钟
Transformers: The State of the Art in NLP 5分钟
The Hugging Face Transformer Pipelines 6分钟
Image Files and Their Processing 4分钟
Convolutional Filters 8分钟
Convolutional Neural Networks for Image Classification 4分钟
Hands-On with Convolutional Neural Networks for Classification 4分钟
Introduction to Vision Transformers 4分钟

4篇阅读材料总计180分钟

Essential Reading: Deep Learning with Python and TensorFlow 60分钟
Recommended Reading: Resources for Learning Natural Language Processing 30分钟
Essential Reading: Deep Learning with Python and TensorFlow 60分钟
Recommended Reading: Are Transformers Better Than CNNs at Image Recognition? 30分钟