Artificial Intelligence

After completing a class on Artificial Intelligence I learned that many universities use the same textbook and many of the examples from this book are used in lectures about Artificial Intelligence.  It is a great resource!  The Coursera class uses the same examples as well as my Georgia Tech Class.  I am sure many AI classes use the same examples.  That can be very helpful when discussing AI with other people, as you have a common ground.

Artificial Intelligence: A Modern Approach Textbook

Here is the link to the textbook site, as well as a link to the code from the book. The link has repositories for implementations of the AI algorithms in Python, Java and many other languages.

Textbook: Artificial Intelligence: A Modern Approach (http://aima.cs.berkeley.edu/)
Code from the book: https://github.com/aimacode

Artificial Intelligence Topics

1. Problem Solving
   • Search (Basic search algorithms.  BFS, DFS)
   • Informed Search (A*, Greedy, Hill-climbing)
   • Constraint Satisfaction (CSP, Backtracking)
   • Adversarial Search (Games, Minimax, AB Pruning)
2. Knowlege and reasoning
   • Logical Agents (KBAI, Reasoning, Propositional Logic Agents)
   • Inference in First-Order Logic (Forward chaining, backward chaining)
   • Knowledge Representation
3. Planning
   • Planning (States, State-space search, Partial order planning, planning graphs)
   • Planning in the real world (Nondeterministic Domains, Conditional Planning, Continous Planning)
4. Uncertain knowledge and reasoning
   • Uncertainty (Probability, Joint distributions, Independence, Bayes’ Rule)
   • Probabilistic Reasoning (Bayesian Networks, Conditional Distributions, Inference in Bays networks)
   • Probabilistic Reasoning over Time (Temporal models, Hidden Markov Models (HMMs), Kalman Filters, Dynamic Bayesian Networks (DBNs)
   • Decision Making (UtilitytTheory, Utility functions, Decision Networks, Game theory)
5. Learning
   • Learning from Observations (Inductive Learning, Learning Decision Trees, Ensemble Learning)
   • Knowledge in Learning (Explanation-Based Learning)
   • Statistical Learning Methods (Naive Bayes models, Learning from BN, HMMs, Neural Networks)
   • Reinforcement Learning (Passive and active reinforcement learning)
6. Communicating, perceiving and acting
   • Perception (Image processing, 3D information, Motion, Object recognition)
   • Robotics (Sensors, Effectors, Localization, Mapping, Planning, Moving)

Even the cover of the book is interesting!