About this course: This course will provide you a foundational understanding of machine learning models (logistic regression, multilayer perceptrons, convolutional neural networks, natural language processing, etc.) as well as demonstrate how these models can solve complex problems in a variety of industries, from medical diagnostics to image recognition to text prediction. In addition, we have designed practice exercises that will give you hands-on experience implementing these data science models on data sets. These practice exercises will teach you how to implement machine learning algorithms with TensorFlow, open source libraries used by leading tech companies in the machine learning field (e.g., Google, NVIDIA, CocaCola, eBay, Snapchat, Uber and many more).
Who is this class for: This course is for anyone interested in learning the basics of machine learning (ML), and on how it is applied in multiple settings. You will need some experience programming in Python as well as some basic math skills to succeed in this course. Duke's Data Science Math Skills provides a solid foundation in math for data science: https://www.coursera.org/learn/datasciencemathskills/. And there are many great introductory Python courses online.
Created by: Duke University
Taught by: Lawrence Carin , James L. Meriam Professor of Electrical and Computer Engineering
Electrical and Computer Engineering
| Level | Intermediate |
| Commitment | 4 weeks of study, 2-5 hours/week |
| Language | English |
| How To Pass | Pass all graded assignments to complete the course. |
Syllabus
WEEK 1
Simple Introduction to Machine Learning
The focus of this module is to introduce the concepts of machine learning with as little mathematics as possible. We will introduce basic concepts in machine learning, including logistic regression, a simple but widely employed machine learning (ML) method. Also covered is multilayered perceptron (MLP), a fundamental neural network. The concept of deep learning is discussed, and also related to simpler models.
24 videos, 1 reading, 9 practice quizzes
- Video: What Is Machine Learning?
- Practice Quiz: Intro to Machine Learning
- Video: Logistic Regression
- Video: Interpretation of Logistic Regression
- Reading: Math for Data Science
- Video: Motivation for Multilayer Perceptron
- Practice Quiz: Logistic Regression
- LTI Item: Jupyter Notebook: Python Prerequisites
- Video: Multilayer Perceptron Concepts
- Video: Multilayer Perceptron Math Model
- Practice Quiz: Multilayer Perceptron
- Video: Deep Learning
- Video: Example: Document Analysis
- Video: Interpretation of Multilayer Perceptron
- Video: Transfer Learning
- Practice Quiz: Deep Learning
- Video: Model Selection
- Practice Quiz: Model Selection
- Video: Early History of Neural Networks
- Video: Modern History of Neural Networks
- Practice Quiz: History of Neural Networks
- Video: Hierarchical Structure of Images
- Video: Convolution Filters
- Video: Convolutional Neural Network
- Practice Quiz: CNN Concepts
- Video: CNN Math Model
- Video: How the Model Learns
- Video: Advantages of Hierarchical Features
- Practice Quiz: CNN Math Model
- Video: CNN on Real Images
- Video: Applications in Use and Practice
- Video: Deep Learning and Transfer Learning
- Practice Quiz: Applications In Use and Practice
- LTI Item: Jupyter Notebook: Installing TensorFlow
- Video: Introduction to TensorFlow
- LTI Item: Jupyter Notebook: Overview of Coding Envrionment
- LTI Item: Jupyter Notebook: TensorFlow Basics
Graded: Week 1 Comprehensive
WEEK 2
Basics of Model Learning
In this module we will be discussing the mathematical basis of learning deep networks. We’ll first work through how we define the issue of learning deep networks as a minimization problem of a mathematical function. After defining our mathematical goal, we will introduce validation methods to estimate real-world performance of the learned deep networks. We will then discuss how gradient descent, a classical technique in optimization, can be used to achieve this mathematical goal. Finally, we will discuss both why and how stochastic gradient descent is used in practice to learn deep networks.
6 videos, 2 practice quizzes
- Video: How Do We Evaluate Our Networks?
- Practice Quiz: Lesson One
- Video: How Do We Learn Our Network?
- Video: How Do We Handle Big Data?
- Video: Early Stopping
- Practice Quiz: Lesson 2
- Video: Model Learning with TensorFlow
- LTI Item: Jupyter Notebook: Logistic Regression
- LTI Item: Jupyter Notebook: Multilayer Perceptron Assignment
Graded: Week 2 Comprehensive
WEEK 3
Image Analysis with Convolutional Neural Networks
This week will cover model training, as well as transfer learning and fine-tuning. In addition to learning the fundamentals of a CNN and how it is applied, careful discussion is provided on the intuition of the CNN, with the goal of providing a conceptual understanding.
8 videos, 3 practice quizzes
- Video: Breakdown of the Convolution (1D and 2D)
- Practice Quiz: Lesson One
- Video: Core Components of the Convolutional Layer
- Video: Activation Functions
- Video: Pooling and Fully Connected Layers
- Practice Quiz: Lesson 2
- Video: Training the Network
- Video: Transfer Learning and Fine-Tuning
- Practice Quiz: Lesson 3
- Video: CNN with TensorFlow
- LTI Item: Jupyter Notebook: CNNs
- LTI Item: Jupyter Notebook: CNN Assignment
Graded: Week 3 Comprehensive
WEEK 4
Introduction to Natural Language Processing
This week will cover the application of neural networks to natural language processing (NLP), from simple neural models to the more complex. The fundamental concept of word embeddings is discussed, as well as how such methods are employed within model learning and usage for several NLP applications. A wide range of neural NLP models are also discussed, including recurrent neural networks, and specifically long short-term memory (LSTM) models.
13 videos, 3 practice quizzes
- Video: Words to Vectors
- Video: Example of Word Embeddings
- Practice Quiz: Lesson 1
- Video: Neural Model of Text
- Video: The Softmax Function
- Video: Methods for Learning Model Parameters
- Video: More Details on How to Learn Model Parameters
- Practice Quiz: Lesson 2
- Video: The Recurrent Neural Network
- Video: Long Short-Term Memory
- Video: Long Short-Term Memory Review
- Video: Use of LSTM for Text Synthesis
- Practice Quiz: Lesson 3
- Video: Simple and Effective Alternative Methods for Neural NLP
- Video: Natural Language Processing with TensorFlow
- LTI Item: Jupyter Notebook: NLP
Graded: Week 4 Comprehensive
FAQs
How It Works
Coursework
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Help from Your Peers
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Certificates
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
Creators
Duke University
Duke University has about 13,000 undergraduate and graduate students and a world-class faculty helping to expand the frontiers of knowledge. The university has a strong commitment to applying knowledge in service to society, both near its North Carolina campus and around the world.
Pricing
| Purchase Course | |
|---|---|
| Access to course materials | Available |
| Access to graded materials | Available |
| Receive a final grade | Available |
| Earn a shareable Course Certificate | Available |
Coursera provides universal access to the world’s best education,
partnering with top universities and organizations to offer courses online.
© 2018 Coursera Inc. All rights reserved.
