Code repository for Advanced Artificial Intelligence Projects with Python, Published By Packt
Switch branches/tags
Nothing to show
Clone or download
Latest commit 88512f9 Apr 2, 2018

README.md

Advanced Artificial Intelligence Projects with Python [Video]

This is the code repository for Advanced Artificial Intelligence Projects with Python [Video], published by Packt. It contains all the supporting project files necessary to work through the video course from start to finish.

About the Video Course

Considered the Holy Grail of automation, data analysis, and robotics, Artificial Intelligence has taken the world by storm as a major field of research and development. Python has surfaced as a dominate language in AI/ML programming because of its simplicity and flexibility, in addition to its great support for open source libraries such as spaCy and TensorFlow. This video course is built for those with a basic understanding of artificial intelligence, introducing them to advanced artificial intelligence projects as they go ahead. The first project introduces natural language processing including part-of-speech tagging and named entity extraction. Wikipedia articles are used to demonstrate the extraction of keywords, and the Enron email archive is mined for mentions and relationships of people, places, and organizations. The spaCy library is used. The next project introduces genetic algorithms. The DEAP library is used. A music data set is used in a genetic algorithm that generates a music playlist satisfying multiple criteria such as song similarity and playlist length. The last project introduces reinforcement learning and deep reinforcement learning. The OpenAI Gym platform and Q-learning algorithm are used to build a game-playing AI.

What You Will Learn

  • Extract names, places, and more and their relationships from text
  • Build a recommendation engine for finding new music
  • Use deep reinforcement learning to build an AI that plays arcade games
  • Employ the SpaCy and textacy libraries for natural language processing
  • Use popular libraries such as Keras and TensorFlow for reinforcement learning

Instructions and Navigation

Assumed Knowledge

To fully benefit from the coverage included in this course, you will need:

● Prior working knowledge of the Python language

● Familiarity with Python library installation tools (such as Pip)

● (Optional) Experience with other AI concepts like classification and neural networks

● (Optional) Experience with Jupyter notebook for Python coding

Technical Requirements

This course has the following software requirements:

● An editor like Atom, Sublime Text or Visual Studio Code or Jupyter notebook

● Python 3

● spaCy

● DEAP

● essentia

● OpenAI Gym

● NumPy

This course has been tested on the following system configuration:

● OS: macOS Sierra (10.12)

● Processor: 2.4 GHz Intel Core i5

● Memory: 8 GB

● Hard Disk Space: 700 MB (mostly Python packages), 950 GB for music dataset used in Project 2

● Video Card: Intel Iris, 1.5 GB Video Memory

Related Products