- Intro-Inference
- Search
- Game tree and graph pruning
- Blocks world and Rejecting symbolic AI
- AI-inspiration
- ACO and PSO
- Neural evaluation
- Learning perceptron and delta
- Backprop and competitive
- GA algorithm
- GA operators
- Reinforcement Learning
- Robotics
This unit introduced Informed search or heuristic search. Uniformed search, or blind search. Then it explores Search algorithms like Brute-Force algorithms like Breadth-First search, Breadth-Best Search, Depth-First Search, and A* Search. For a visulization for these algorithms, you can refer to: https://algorithm-visualizer.org/
Breadth-first search
Depth first search
Best search
A*
using Min-Max with games such as: Tic Tac Toe Stone game
OnTable(a,b), HandsEmpty()
The natural intelligence and animals; inspired by ants, and birds' swarm
Example of natural intelligence is:
Ant Colony optomization ACO
Practical swarm optimization PSO
Hidden layer
Output layer
Delta rule
Winning node
Genatic Algorithm
Calculate the over all probability of all values
Draw Roloutte Wheel
Calclute Fitness
mutation probability
When the number is less than the probability we will switch the number to the other value. E.g 0 to 1, and vise versa
Mating Pool
mutation probability
Reinforcement Learning
Q(state, Action) = Reward(s,a)+ Y(Max(s,a))