Course Information
Registration period
Year-round Recruitment
Course Level
Study Mode
Duration
1 Hour(s) 44 Minute(s)
Language
English
Taught by
Milo Spencer-Harper
Rating
Course Overview
How to teach a neural network to play a game using delayed gratification in 146 lines of Python code
This course is designed for beginners to machine learning. Some of the most exciting advances in artificial intelligence have occurred by challenging neural networks to play games. I will introduce the concept of reinforcement learning, by teaching you to code a neural network in Python capable of delayed gratification.
We will use the NChain game provided by the Open AI institute. The computer gets a small reward if it goes backwards, but if it learns to make short term sacrifices by persistently pressing forwards it can earn a much larger reward. Using this example I will teach you Deep Q Learning - a revolutionary technique invented by Google DeepMind to teach neural networks to play chess, Go and Atari.
Course Content
- 5 section(s)
- 24 lecture(s)
- Section 1 Introduction
- Section 2 Creating your Agent and Environment
- Section 3 Q Learning
- Section 4 Neural Networks
- Section 5 Deep Q Learning
What You’ll Learn
- Machine Learning
- Artificial Intelligence
- Neural Networks
- Reinforcement Learning
- Deep Q Learning
- OpenAI Gym
- Keras
- Tensorflow
- Bellman Equation
Skills covered in this course
Reviews
-
JJstan
I really liked this course. It did help with my understanding of AI. However, I had to troubleshoot several items to progress in a couple sections.
-
MMourad Ben Youcef
Excellent! A lot to learn. Will be appreciated if we can have practical courses from start to finish !
-
AAlex Wood
This course was fantastic as it was able to teach me about neural networks despite having little prior knowledge. If anyone is looking to learn about AI, then this a great starting point
-
JJack Santiago
Couldn't run it as couldn't get Tensorflow to run and it said it couldn't install when I tried to reinstall as it said the long path support wasn't enabled (using windows 10).
