cs221_l1

reflex-based model

e.g. linear classifiers deep neural networks

Fully feed-forward(no backtracking), no reasoning about what was going on

state-based model

e.g. 在下国际象棋的时候 白棋怎么走下一步，这种需要一定的推理的玩意儿

Search problem

Markov decision processes

Adversarial games

Variable-based models

Constraint satisfaction problems: hard constraints(e.g. sudoku, scheduling) Bayesian networks: soft dependencies(e.g. tracking cars from sensors)