Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI. In this class, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself. More importantly, you'll learn about not only the theoretical underpinnings of learning, but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. Finally, you'll learn about some of Silicon Valley's best practices in innovation as it pertains to machine learning and AI.
This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI). The course will also draw from numerous case studies and applications, so that you'll also learn how to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.
Type of Material:
Online Course Module
Recommended Uses:
self-paced learning; individual; lecture;
Technical Requirements:
Web browswer
Identify Major Learning Goals:
Upon completion of this course, students will be able to:
1. describe the concept and usage of machine learning;
2. explain different machine learning methods like linear regression, logistic regression, neural network, etc.;
3. apply machine learning techniques to solve problems.
The course covers a borad spectrum of topics in machine learning. These topics are very essential for beginners to learn the concept of maching learning and how to apply these techniques in different problems. The materials are very clear and accurate. It is very useful for students to support their on-going research or profession development.
- It mentions different aspects of the usage of machine learning, in computer science, medical, handwriting recognitions, NLP, and so on.
- It used examples of Google search and DNA gene to illustrate the idea of classification, which is commonly used in many other different course, so users should find the cases not difficult to understand and imgine.
- It is good to use daily examples first and not to use many codes in the begining so that learners can get the main concepts before going into some formal definitions or detailed coding.
Concerns:
Limited perspective on Machine Learning.
Potential Effectiveness as a Teaching Tool
Rating:
Strengths:
The learning goals of each chapters are very clear. It help begineers to acquire the concepts and re-inforce their concepts. The quizzes can effectively help students to assess themselves. It is easy for instructors to integrate it into their lectures or daily classes.
- Some very good examples are given, e.g. the cocktail problem being solved by a single line of the coding introduced in unsupervised learning is very illustrative on the power of appropriate coding.
- With the translation features provided by the platform, many choices of the languages are available. For sure, I can't comment on the accurancy of each language, but the translation of English and Chinese is quite accurate.
- It uses the programming language of Matlab or octave.
- The pace of the speech and the text displayed is clear to follow and read.
Ease of Use for Both Students and Faculty
Rating:
Strengths:
The courses are easy to follow since it is divided into a number of essential topics. The learning goals of each chapter are clear. It contains a number of videos which are clear and effectively illustrate the concepts of machine learning.
- For the quick review questions, using the feature in Coursera, the user can get instead response on the answer given. After each question, explanations to the answers are also given.
- It provided video and texts based learning materials. While the video does not much animations or fancy graphics, the content and presentation is clear by text.
- It also provides some codes that can be run directly in the web site, so the problem of the need to install Matlab or Octave in the user's platform is greatly relieved.
Concerns:
Difficulty in actually accessing the course materials themselves. Multiple attempts to access the course proved unsuccessful.
The duration of videos varies a lot. Some are just few minutes while some are over 20 minutes. Instructors need to be aware of this if they want to use them in their lectures.
It may even more effective in terms of learning if some links of further references are given immediately after a topic.
Creative Commons:
Search by ISBN?
It looks like you have entered an ISBN number. Would you like to search using what you have
entered as an ISBN number?
Searching for Members?
You entered an email address. Would you like to search for members? Click Yes to continue. If no, materials will be displayed first. You can refine your search with the options on the left of the results page.
Searching for Members?
You entered an email address. Would you like to search for members? Click Yes to continue. If no, materials will be displayed first. You can refine your search with the options on the left of the results page.
