CS 188 notes berkeley.edu
sp24-lec01
What should we build?
A human being should be able to change a diaper, plan an invasion,
butcher a hog, conn a ship, design a building, write a sonnet, balance
accounts, build a wall, set a bone, comfort the dying, take orders, give
orders, cooperate, act alone, solve equations, analyze a new problem,
pitch manure, program a computer, cook a tasty meal, fight efficiently,
die gallantly. Specialization is for insects.
—Robert A. Heinlein
1943 to present
What Can AI Do? Quiz
from Note 1
PEAS (Performance Measure, Environment, Actuators, Sensors)
an environment has known physics, then the transition model (even if stochastic) is known to the agent and it can use that when planning a path
https://blogbarley.blogspot.com/2025/09/rough-draft-25248-pt1-simulation-rapid.html physics rules required
cs188-sp24-lec02
Depth-First versus Breadth-First Search
Uniform Cost Search
Plan versus Reflex Agent
A state space, A successor function, A start state and a goal test [tokenization and Reward]
-Neural network sketch, Quantum computing sketch -similarity
 |
| IBM-Quantum-Learning-Tutorials/EPR-paradox.ipynb |
neuron image: data pull to optic hologram (Cybernetic) constraint-solving algorithm
Search Methods Quiz: DFS vs BFS
The bad: Explores options in every direction & No information about goal location -slime mold is more advanced https://www.nps.gov/articles/000/slime-molds.htm
nodes = world configurations
priority queue
No comments:
Post a Comment