(The below text version of the notes is for search purposes and convenience. See the PDF version for proper formatting such as bold, italics, etc., and graphics where applicable. Copyright: 2022 Retraice, Inc.)
AIMA4e Annotations
A companion to the great white brick.
As of November 24, 2022
(Start date: November 21, 2022.)
[1]retraice.com
Version notes: [2]Retraice ([3]2022/11/21) (Re57), first draft, covered Preface, Sections I, II; [4]Retraice ([5]2022/11/22) (Re58), no footnotes, covered Sections III, IV; [6]Retraice ([7]2022/11/22) (Re58) again, moved some notes from Re57 and Re58 notes to footnotes here;
[8]Retraice ([9]2022/11/23) (Re59), covered Sections V, VI, VII.
PREFACE
* The phenomenon: intelligent agents[10]^1
* The discipline: artificial intelligence,[11]^2 "the study of agents that receive percepts from the environment and perform actions." (vii)
* Aspects of the phenomenon:
+ Agent function: "Each ...agent implements a function that maps percept sequences to actions" (vii)
o Ways to represent agent functions include: "reactive agents, real-time planners, decision-theoretic systems, and deep learning systems." (vii)
+ Learning
o "a construction method for competent systems" (viii)
o "a way of extending the reach of the designer into unknown environments." (viii)
+ Goals
o Robotics and vision:
# "not ...independently defined problems"
# "[things] in the service of achieving goals."
I INTELLIGENCE --"Artificial Intelligence"
1 Intro:
definitions, foundations, history, philosophy, state of the art, risks-benefits
2 Agents:
environments, `good' behavior, agent structure and types
II SOLVING--"Problem-solving"
3 Searching:
Looking ahead to find a sequence.
Algorithms, strategies, informed/heuristic[12]^3 strategies.
4 Complex Environments:
More realistic environments.
Local search, optimization, continuous spaces, nondeterministic actions, partially observable env.s, online search and unknown env.s.
5 Adversarial Games:
Other agents competing against us.
Theory, optimal decisions, alpha-beta tree search, Monte Carlo tree search, stochastic g.s, partially observable g.s, limitations.
6 Constraint Satisfaction Problems:
States as domains, solutions as allowable combinations of states.
Constraint propagation, inference, backtracking search, local search, structure of problems
III THINKING--"Knowledge, reasoning, and planning"
7 Logical Agents:
Forming representations and reasoning before acting.
Knowledge-based agents; representing[13]^4 worlds; logic, world models and `possible worlds';[14]^5 logic without objects.
8 First-Order Logic:
A formal language for objects and their relations.
`Ontological commitment' (what is assumed about reality); syntax, semantics; knowledge engineering (building formal representations of important[15]^6 objects and relations in a domain).
9 First-Order Inference:
Reasoning about objects and their relations.
Algorithms to answer any 1st-order logic question.
10 Knowledge Representation:
Representing the real world for problem solving.
What content to put into a knowledge base.
Knowledge representation languages and their uses (315):
* First-order logic: reasoning about a world of objects and relations;
* Hierarchical task networks: for reasoning about plans (chpt. 11);
* Bayesian networks: for reasoning with uncertainty (chpt. 13);
* Markov models: for reasoning over time (chpt. 17);
* Deep neural networks: for reasoning about images, sounds, other data (chpt. 21).
11 Automated Planning:
Hierarchical task networks.
Planning for spacecraft, factories, military campaigns; representing actions and states; efficient algorithms and heuristics.
IV UNCERTAINTY--"Uncertain knowledge and reasoning"
12 Quantifying Uncertainty:
An answer to the laziness and ignorance that kill formal logic.
Causes of uncertainty are environment types (partially observable,[16]^7 nondeterministic, adversarial[17]^8 ); belief state grows big and unlikely fast (384); agents still need a way to act; absolute certainty is impossible;[18]^9 it comes down to importance, likelihood and degree of success (385-386).
Logic fails because laziness and ignorance; probability theory solves the qualification problem by summarizing the uncertainty.[19]^10
* Laziness: too much work to list everything, or use such a list;
* Ignorance: (theoretical) there are no complete theories; (practical) we can never run all the tests.
13 Probabilistic Reasoning [big]:
Bayesian networks.
For reasoning with uncertainty by representing causal independence (398) and conditional independence (401) relationships to simplify probabilistic representations of the world.
14 Probabilistic Reasoning Over Time:
Comprehending the uncertain past, present and future.
[20]^11
Belief state plus transition model yields prediction (chpt 4, 7, 11); percepts and sensor model yield updated belief state; add probability theory to switch from possible states to probable states.[21]^12
15 Probabilistic Programming:
Universal formal languages to represent any computable probability model, and they come with algorithms.
Using formal logic and traditional programming languages to represent probabilistic information.
16 Making Simple Decisions:
Agents getting what they want in an uncertain world--as much as possible, on average.
Beliefs, desires; utility theory; utility functions; decision networks; the value of information (547);[22]^13 this chapter is concerned with one-shot or episodic decisions problems (as opposed to sequential) (cf. 562, below).
17 Making Complex Decisions:
What to do today given decisions to be made tomorrow.
Sequential decision problems (as opposed to one-shot episodic, cf. above): the agent's utility depends on a sequence of decisions in stochastic (explicitly probabilistic (45)) and partially observable environments. Markov models (563; cf. 463) for reasoning over time (chpt. 17).
18 Multiagent Decision Making [big]:
When there's more than one agent in the environment.
The nature of such environments and the strategies for problem-solving depend on the relationships between agents: non-cooperative and cooperative game theory; collective decision-making.
V LEARNING--"Machine learning"
19 Learning From Examples [big]:
Improving behavior by observing the present (past?) and predicting the future.
Learning is improving performance (behavior) after making observations.[23]^14
If the agent is a computer: Machine learning: "a computer observes some data, builds a model based on the data, and uses the model as both a hypothesis about the world and a piece of software that can solve problems." (651)
Subsections:
* supervised learning;
* learning decision trees;
* model selection and optimization;
* theory of learning;
* linear regression (finding the best-fit line, i.e. predicting `future' [dependent] values based on plotting `past' [independent] values), classification;[24]^15
* nonparametric models (which retain all the examples, aka `instance-based' or `memory-based' learning, which is more true to large datasets [scalable?] than parametric, which summarize, and then discard, training data in fixed numbers of parameters),
* ensemble learning (using multiple hypotheses instead of one, and averaging or voting--`base' models are combined into an `ensemble' model);
* ML system development, the practice (software engineering and design patters in ML ops).
20 Learning Probabilistic Models:
View `learning' as "uncertain reasoning from observations" and model the world accordingly.
Agents can't use probability and decision theories until they learn them from experience: treat learning itself as an inference process in a probabilistic world. Use Bayesian networks. Key concepts: data and hypotheses. "Here, the data are evidence ...instantiations of some or all of the random variables describing the domain."[25]^16
21 Deep Learning:
represent hypotheses as "complex algebraic circuits with tunable connection strengths."
The circuits are orginzed into layers, a multi-step computation path. Ideal for recognizing, translating and generating images (including objects in images) and speech; `neural networks'.
From chpt. 10 on knowledge rep. languages, above notes: "deep neural networks: for reasoning about images, sounds, other data."
Think: gradient descent, back-propagation, convolutional neural networks.
22 Reinforcement Learning:
Learning from experiences of reward and punishment instead of correct examples from a supervisor
Passive and active RL., Q-learning, apprenticeships and inverse RL.
Cf. Reward is Enough, May 2021: [26]https://www.deepmind.com/publications/reward-is-enough
VI INTERACTING--"Communicating, perceiving, and acting"
23 Natural Language Processing:
Communicating with humans and learning from what they've written.
Language model: "a probability distribution describing the likelihood of any string." (824)
N-grams, grammar, syntax, semantics, parsing, vagueness, ambiguity, quantification.
24 Deep Learning for Natural Language Processing:
Using neural nets on natural language to effectively handle the complexity.
"[R]epresenting words as points in a high-dimensional space." RNNs for "long-distance context."
Cf. Attention Is All You Need, 2017: [27]https://arxiv.org/abs/1706.03762 and AIMA4e p. 868, transformer architecture, self-attention.
25 Computer Vision:
Connecting AI to cameras.
Photons provide a lot of valuable information to agents--too much information.
Surveillance cameras--good and bad; cars. Lots of machines do better if they can see.
From the Preface: Robotics and vision: "not ...independently defined problems"..."[things] in the service of achieving goals."
26 Robotics:
Connecting AI to sensors, effectors and actuators
To enable movement in-and of--the physical world. Cars, spacecraft, surgeons, submarines, delivery bots.
From the Preface: Robotics and vision: "not ...independently defined problems"..."[things] in the service of achieving goals."
VII CONCLUSIONS--"Conclusions"
27 Philosophy, Ethics, and Safety of AI:
What is AI? What should we do with it? What might it do with us?
Trust--of systems, humans, ourselves, each other.
The human use of human beings. Usefulness of human beings at all?
Medicine. War.
28 The Future of AI:
Our tools will improve dramatically; our ends might remain the same.
Our preferences, our tools, our architectures. They're ours, for now.
Minimize the negative impacts, don't maximize the positive?
A: MATH--"Appendix A: Mathematical Background"
B: CODE--"Appendix B: Notes on Languages and Algorithms"
__
References
Aleksandrov, A. D., Kolmogorov, A. N., & Lavrent'ev, M. A. (1969). Mathematics: Its Content, Methods and Meaning (3 Volumes in One). Dover, 1999 reprint ed. ISBN: 0486409163. Searches:
[28]https://www.amazon.com/s?k=0486409163
[29]https://www.google.com/search?q=isbn+0486409163
[30]https://lccn.loc.gov/99033023
Bulmer, M. G. (1967). Principles of Statistics. Dover, 1979 reprint ed. ISBN: 0486637603. Searches:
[31]https://www.amazon.com/s?k=0486637603
[32]https://www.google.com/search?q=isbn+0486637603
[33]https://lccn.loc.gov/78072991
Crawford, K. (2021). Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence. Yale University Press. ISBN: 978-0300209570. Searches:
[34]https://www.amazon.com/s?k=9780300209570
[35]https://www.google.com/search?q=isbn+9780300209570
[36]https://lccn.loc.gov/2020947842
Frankfurt, H. G. (1988). The Importance of What We Care About. Cambridge. ISBN: 978-0521336116. Searches:
[37]https://www.amazon.com/s?k=978-0521336116
[38]https://www.google.com/search?q=isbn+978-0521336116
[39]https://lccn.loc.gov/87026941
Gerrish, S. (2018). How Smart Machines Think. The MIT Press. ISBN: 978-0262038409. Searches:
[40]https://www.amazon.com/s?k=9780262038409
[41]https://www.google.com/search?q=isbn+9780262038409
[42]https://lccn.loc.gov/2017059862
Kahneman, D. (2011). Thinking, Fast and Slow. Farrar, Straus and Giroux. ISBN: 978-0374533557. Searches:
[43]https://www.amazon.com/s?k=978-0374533557
[44]https://www.google.com/search?q=isbn+978-0374533557
[45]https://lccn.loc.gov/2012533187
Kramer, E. E. (1970). The Nature and Growth of Modern Mathematics. Hawthorn Books. No ISBN. Searches:
[46]https://www.amazon.com/s?k=kramer+nature+and+growth+of+modern+mathematics
[47]https://www.google.com/search?q=kramer+nature+and+growth+of+modern+mathematics
[48]https://lccn.loc.gov/73091317
Macphail, E. M. (1982). Brain and Intelligence in Vertebrates. Oxford. ISBN 0198545517. Searches:
[49]https://www.amazon.com/s?k=0198545517
[50]https://www.google.com/search?q=isbn+0198545517
[51]https://lccn.loc.gov/82166301
Retraice (2020/09/07). Re1: Three Kinds of Intelligence. retraice.com.
[52]https://www.retraice.com/segments/re1 Retrieved 22nd Sep. 2020.
Retraice (2020/11/02). Re10: Living to Guess Another Day. retraice.com.
[53]https://www.retraice.com/segments/re10 Retrieved 2nd Nov. 2020.
Retraice (2020/11/10). Re13: The Care Factor. retraice.com.
[54]https://www.retraice.com/segments/re13 Retrieved 10th Nov. 2020.
Retraice (2020/11/25). Re15: Trust and Sources. retraice.com.
[55]https://www.retraice.com/segments/re15 Retrieved 28th Feb. 2022.
Retraice (2022/10/19). Re23: You Need a World Model. retraice.com.
[56]https://www.retraice.com/segments/re23 Retrieved 20th Oct. 2022.
Retraice (2022/10/23). Re27: Now That's a World Model - WM4. retraice.com.
[57]https://www.retraice.com/segments/re27 Retrieved 24th Oct. 2022.
Retraice (2022/10/31). Re36: Notes on Conspiracy. retraice.com.
[58]https://www.retraice.com/segments/re36 Retrieved 4th Nov. 2022.
Retraice (2022/11/12). Re48: From Drugs to Mao to Money. retraice.com.
[59]https://www.retraice.com/segments/re48 Retrieved 14th Nov. 2022.
Retraice (2022/11/16). Re52: Big Questions About AI. retraice.com.
[60]https://www.retraice.com/segments/re52 Retrieved 17th Nov. 2022.
Retraice (2022/11/21). Re57: AI, Agents, Problem-solving, Searching, Environments, Games (AIMA4e chpts. 1-6). retraice.com.
[61]https://www.retraice.com/segments/re57 Retrieved 22nd Nov. 2022.
Retraice (2022/11/22). Re58: Thinking and Uncertainty (AIMA4e chpts. 7-18). retraice.com.
[62]https://www.retraice.com/segments/re58 Retrieved 23rd Nov. 2022.
Retraice (2022/11/23). Re59: Learning, Interacting, Conclusions (AIMA4e chpts. 19-28). retraice.com.
[63]https://www.retraice.com/segments/re59 Retrieved 24th Nov. 2022.
Russell, B. (1948). Human Knowledge: Its Scope and Limits. Routledge. First published in 1948. This edition 1992. ISBN: 0415083028. Searches:
[64]https://archive.org/search.php?query=Human%20Knowledge%3A%20Its%20Scope%20and%20Limits
[65]https://www.amazon.com/s?k=0415083028
[66]https://www.google.com/search?q=isbn+0415083028
[67]https://lccn.loc.gov/94209784
Vallee, J. (1979). Messengers of Deception: UFO Contacts and Cults. And/Or Press. ISBN: 0915904381. Different edition and searches:
[68]https://archive.org/details/MessengersOfDeceptionUFOContactsAndCultsJacquesValle1979/mode/2up
[69]https://www.amazon.com/s?k=0915904381
[70]https://www.google.com/search?q=isbn+0915904381
[71]https://catalog.loc.gov/vwebv/search?searchArg=0915904381
References
1. https://retraice.com/
2. XReSeg57
3. XReSeg57
4. XReSeg58
5. XReSeg58
6. XReSeg58
7. XReSeg58
8. XReSeg59
9. XReSeg59
10. fn1x0
11. fn2x0
12. fn3x0
13. fn4x0
14. fn5x0
15. fn6x0
16. fn7x0
17. fn8x0
18. fn9x0
19. fn10x0
20. fn11x0
21. fn12x0
22. fn13x0
23. fn14x0
24. fn15x0
25. fn16x0
26. https://www.deepmind.com/publications/reward-is-enough
27. https://arxiv.org/abs/1706.03762
28. https://www.amazon.com/s?k=0486409163
29. https://www.google.com/search?q=isbn+0486409163
30. https://lccn.loc.gov/99033023
31. https://www.amazon.com/s?k=0486637603
32. https://www.google.com/search?q=isbn+0486637603
33. https://lccn.loc.gov/78072991
34. https://www.amazon.com/s?k=9780300209570
35. https://www.google.com/search?q=isbn+9780300209570
36. https://lccn.loc.gov/2020947842
37. https://www.amazon.com/s?k=978-0521336116
38. https://www.google.com/search?q=isbn+978-0521336116
39. https://lccn.loc.gov/87026941
40. https://www.amazon.com/s?k=9780262038409
41. https://www.google.com/search?q=isbn+9780262038409
42. https://lccn.loc.gov/2017059862
43. https://www.amazon.com/s?k=978-0374533557
44. https://www.google.com/search?q=isbn+978-0374533557
45. https://lccn.loc.gov/2012533187
46. https://www.amazon.com/s?k=kramer+nature+and+growth+of+modern+mathematics
47. https://www.google.com/search?q=kramer+nature+and+growth+of+modern+mathematics
48. https://lccn.loc.gov/73091317
49. https://www.amazon.com/s?k=0198545517
50. https://www.google.com/search?q=isbn+0198545517
51. https://lccn.loc.gov/82166301
52. https://www.retraice.com/segments/re1
53. https://www.retraice.com/segments/re10
54. https://www.retraice.com/segments/re13
55. https://www.retraice.com/segments/re15
56. https://www.retraice.com/segments/re23
57. https://www.retraice.com/segments/re27
58. https://www.retraice.com/segments/re36
59. https://www.retraice.com/segments/re48
60. https://www.retraice.com/segments/re52
61. https://www.retraice.com/segments/re57
62. https://www.retraice.com/segments/re58
63. https://www.retraice.com/segments/re59
64. https://archive.org/search.php?query=Human%20Knowledge%3A%20Its%20Scope%20and%20Limits
65. https://www.amazon.com/s?k=0415083028
66. https://www.google.com/search?q=isbn+0415083028
67. https://lccn.loc.gov/94209784
68. https://archive.org/details/MessengersOfDeceptionUFOContactsAndCultsJacquesValle1979/mode/2up
69. https://www.amazon.com/s?k=0915904381
70. https://www.google.com/search?q=isbn+0915904381
71. https://catalog.loc.gov/vwebv/search?searchArg=0915904381
