https://github.com/raphsenn/ai-notebooks

Some ai notebooks about Rational agents, Searching, Constraint satisfaction, Board games, Machine learning, Deep learning.
https://github.com/raphsenn/ai-notebooks

artificial-intelligence board-game deep-learning machine-learning neural-network python3 rational-agent search-algorithm searching-algorithms

Last synced: 3 months ago
JSON representation

Some ai notebooks about Rational agents, Searching, Constraint satisfaction, Board games, Machine learning, Deep learning.

• Host: GitHub
• URL: https://github.com/raphsenn/ai-notebooks
• Owner: raphsenn
• License: mit
• Created: 2024-08-22T06:39:11.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-11-12T14:30:52.000Z (3 months ago)
• Last Synced: 2024-11-12T15:30:49.307Z (3 months ago)
• Topics: artificial-intelligence, board-game, deep-learning, machine-learning, neural-network, python3, rational-agent, search-algorithm, searching-algorithms
• Language: Jupyter Notebook
• Homepage:
• Size: 3.62 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# ai-notebooks

Some ai notebooks about Rational agents, Searching, Constraint satisfaction, Board games, Machine learning, Deep learning.

## Topics

* AI-Agents

* Search Algorithms

* Constraint Satisfaction Problems

* Board Games

* Planning

* Making Simple Decision Under Uncertainty

* Acting under Uncertainty

* Machine Learning

* Deep Learning

* Optimization Algorithms (Theorie)

## AI-Agents

* What is an agent?

* Rational agents

* Rationallity

* Structure of an AI agent

* PEAS Representation

* Agent environment in AI

* Example implementation of vacuum cleaner

## Search Algorithms

* Uniformed Search methods

* Informed Search methods

## Constraint Satisfaction Problems

* Backtracking Algorithm

## Board Games

* MiniMax algorithm 

* MiniMax (with alpha beta purning)

* Solving games (TicTacToe, Sudoku, ..)

## Machine Learning

* Linear Methods

* Priciples of Regularization

* Support Vector Machines

* Decision Trees

* Neural Networks

* Ensembles

* Gradient Boosted Decision Trees

* Hyperparameter Optimization

* Fighting Overfitting

* Error measures