AIPrimer.AI
  • 🚦AI Primer In Transportation
  • CHAPTER 1 - INTRODUCTION TO MACHINE LEARNING
    • Machine Learning in Transportation
    • What is Machine Learning?
    • Types of Machine Learning
      • Supervised Learning
      • Unsupervised Learning
      • Semi-supervised Learning
      • Reinforced Learning
    • Fundamental concepts of machine learning
      • Model Training and Testing
      • Evaluating the Model’s Prediction Accuracy
      • The Underfitting and Overfitting Problems
      • Bias-Variance Tradeoff in Overfitting
      • Model Validation Techniques
      • Hyperparameter Tuning
      • Model Regularization
      • The Curse of Ddimensionality
    • Machine Learning versus Statistics
  • CHAPTER 2 - SUPERVISED METHODS
    • Supervised Learning_Complete Draft
    • K-Nearest Neighbor (KNN) Algorithm
    • Tree-Based Methods
    • Boosting
    • Support Vector Machines (SVMs)
  • CHAPTER 3 - UNSUPERVISED LEARNING
    • Principal Component Analysis
      • How Does It Work?
      • Interpretation of PCA result
      • Applications in Transportation
    • CLUSTERING
      • K-MEANS
      • SPECTRAL CLUSTERING
      • Hierarchical Clustering
    • REFERENCE
  • CHAPTER 4 - NEURAL NETWORK
    • The Basic Paradigm: Multilayer Perceptron
    • Regression and Classification Problems with Neural Networks
    • Advanced Topologies
      • Modular Network
      • Coactive Neuro–Fuzzy Inference System
      • Recurrent Neural Networks
      • Jordan-Elman Network
      • Time-Lagged Feed-Forward Network
      • Deep Neural Networks
  • CHAPTER 5 - DEEP LEARNING
    • Convolutional Neural Networks
      • Introduction
      • Convolution Operation
      • Typical Layer Structure
      • Parameters and Hyperparameters
      • Summary of Key Features
      • Training of CNN
      • Transfer Learning
    • Recurrent Neural Networks
      • Introduction
      • Long Short-Term Memory Neural Network
      • Application in transportation
    • Recent Development
      • AlexNet, ZFNet, VggNet, and GoogLeNet
      • ResNet
      • U-Net: Full Convolutional Network
      • R-CNN, Fast R-CNN, and Faster R-CNN
      • Mask R-CNN
      • SSD and YOLO
      • RetinaNet
      • MobileNets
      • Deformable Convolution Networks
      • CenterNet
      • Exemplar Applications in Transportation
    • Reference
  • CHAPTER 6 - REINFORCEMENT LEARNING
    • Introduction
    • Reinforcement Learning Algorithms
    • Model-free v.s. Model-based Reinforcement Learning
    • Applications of Reinforcement Learning to Transportation and Traffic Engineering
    • REFERENCE
  • CHAPTER 7 - IMPLEMENTING ML AND COMPUTATIONAL REQUIREMENTS
    • Data Pipeline for Machine Learning
      • Introduction
      • Problem Definition
      • Data Ingestion
      • Data Preparation
      • Data Segregation
      • Model Training
      • Model Deployment
      • Performance Monitoring
    • Implementation Tools: The Machine Learning Ecosystem
      • Machine Learning Framework
      • Data Ingestion tools
      • Databases
      • Programming Languages
      • Visualization Tools
    • Cloud Computing
      • Types and Services
    • High-Performance Computing
      • Deployment on-premise vs on-cloud
      • Case Study: Data-driven approach for the implementation of Variable Speed Limit
      • Conclusion
  • CHAPTER 8 - RESOURCES
    • Mathematics and Statistics
    • Programming, languages, and software
    • Machine learning environments
    • Tools of the Trade
    • Online Learning Sites
    • Key Math Concepts
  • REFERENCES
  • IMPROVEMENT BACKLOG
Powered by GitBook
On this page
  1. CHAPTER 8 - RESOURCES

Online Learning Sites

PreviousTools of the TradeNextKey Math Concepts

Last updated 1 year ago

On-line learning is one of the best ways to learn about machine learning and the necessary background. Typical course content includes video lectures, short quizzes after each section, and possibly intermediate or final exams. Courses offer official certificates of completion for a small fee; users who do not with to pay the fee can usually audit the courses for free.

Some courses follow a schedule and are only offered for a limited amount of time; although course content may be available in archived form later on. Other courses are self-paced and available on demand.

Coursera [67] and edX [68] in particular have a number of useful courses on machine learning, computer science, statistics, and mathematics. Udacity [71] is a commercial site that usually requires a fee for its courses.

MIT began its OpenCourseWare site [70] more than 15 years ago. Most courses on machine learning are taught in the Electrical Engineering and Computer Science Department, although machine learning courses are available from other department such as Management. Several courses in Mathematics and Economics departments may also be useful for the mathematical and statistical background they provide.

The Khan Academy [69] was created mainly to assist secondary school students. Some of its courses such as calculus and introductory computer science may be useful for those who require additional background review or study in mathematics or computer science.

Google AI. It does not matter if you’re a seasoned AI/ML expert or merely a beginner, this machine learning online course provides an amazingly rich content set that will boost your AI/ML journey even further. One of the best machine learning course from Google, Learn with Google AI provides participators with a plethora of advanced information for aggravating their machine learning training.

  1. Coursera. A joint effort by a number of universities around the world (including Stanford, Princeton, and Brown), Coursera offers a number of online courses on line in machine learning, mathematics, statistics, and programming. Andrew Ng (Stanford) has a particularly good self-paced introduction to machine learning.

  2. edX. Another on-line cooperative effort of universities around the world, including MIT, Cal, and Harvard; Microsoft is also part of the consortium. A somewhat broader offering of courses than Coursera.

  3. Khan Academy. Has a number of math and computer courses mainly at a secondary school level, including calculus and computer science. Nonetheless, some courses may be useful for those who wish to use machine learning but lack the necessary mathematical background.

  4. MIT OpenCourseWare. MIT began to put its courses online for free beginning in 2002, becoming the first institution of its kind to do so. Now more than 1,200 courses are now available from all MIT departments. Course content varies: some offer only readings and problem sets, while others have video lectures available. (Some of these courses are offered on the edX site [68] as well, with much better coverage and course content.) Most machine learning courses are in the Electrical Engineering department, although other departments – including Economics, Management, and Mathematics – also have courses related to machine learning.

  5. Udacity. Udacity is a private venture, so many of its courses are fee-only. Udacity offers “nanodegrees” in a variety of areas, including machine learning. One of their more interesting courses is on how to build a robot car, reflecting the interest of one of its founders, Sebastian Thrun.

  6. MIT Deep Learning Basics. This class is an introduction to the practice of deep learning through the applied theme of building a self-driving car. It is open to beginners and is designed for those who are new to machine learning, but it can also benefit advanced researchers in the field looking for a practical overview of deep learning methods and their application.

https://ai.google/education/
https://www.coursera.org/
https://www.edx.org/
https://www.khanacademy.org/
https://ocw.mit.edu/index.htm
https://www.udacity.com/
https://selfdrivingcars.mit.edu/