Simply stated: Reinforcement Learning deals with actions and rewards (positive or negative). The rewards help to dictate the future actions.
Many children learn via reinforcement learning. Here is a simple example from my childhood. As a child, I was told not to touch the hot stove.
My action: I touched the door of the hot stove when it was open.
My reward (negative): I burned my hand, and it hurt.
My future actions resulted in me staying away from the hot stove.
This was a very simplified example of reinforcement learning. Here are two more great introductory references:
- Simple Beginner’s guide to Reinforcement Learning
- Deep Learning Research Review: Reinforcement Learning
Last week I spent some time chatting with future data scientists. I set up a camera to record some of the answers. Below are a few of the questions addressed.
- How did I transition to data science?
- Why start a data science project?
- Should a new person focus on machine learning or deep learning?
- What is an example data science project?
- Why is real-time important?
Hopefully the videos and answers are helpful to others. Enjoy! And I kept most of the videos fairly short. If you enjoy the videos, please subscribe to the YouTube channel, Learn Data Science. Also, if you have a question you would like answered, please leave a comment below.
Andrew Ng, co-founder of Coursera and Deep Learning Expert, is launching a new specialization on Coursera. Details can be found at DeepLearning.ai or the Deep Learning Specialization Page. The specialization consists of 5 courses. They are free to audit and watch the videos. There is a fee to get graded assignments and receive a certificate of completion. The first course just started this week, so it is great time to start learning some deep learning.
The last links are not official academic papers, but they are quite good resources on deep learning.
Deep Learning Summer School, Montreal 2016 is aimed at graduate students and industrial engineers and researchers who already have some basic knowledge of machine learning (and possibly but not necessarily of deep learning) and wish to learn more about this rapidly growing field of research. If that is you, there are plenty of videos to help you learn more.
Want to learn about data science and the Internet of Things (IoT)? Futuretext is about to start Data Science for Internet of Things. It is a course aimed at people looking to learn the topics and transition into IoT and data science careers. Here are some quick highlights about the course.
- Starts Mid March 2016 and lasts through December 2016
- Personalized Course
- Available Online
Below is a list of topics.
- Data Science
- Machine Learning
- Data Science for IoT methodology
- Deep Learning
Do check out Data Science for Internet of Things for more details.
I was honored to be able to provide the data science introductory article for the Special Data issue of AL MAGNET magazine. The article is titled, Data Science and the Essential Terms. It provides a description of data science and an example workflow. It also points out some of the key terms in data science and what they mean. The closing describes why now is the time to learn data science.
The magazine is open-access, so you can freely read and share the article. Thank you to the AL MAGNET team for the invitation.