comparison org/ai-journal-review.org @ 384:c135b1d0d0bc

reviewed social network paper.
author Robert McIntyre <rlm@mit.edu>
date Sun, 21 Apr 2013 17:05:30 +0000
parents 31814b600935
children ff0d8955711e
comparison
equal deleted inserted replaced
383:31814b600935 384:c135b1d0d0bc
1 #+title:Interesting Papers in Artificial Intelligence 1 #+title:Interesting Papers in Artificial Intelligence
2 2
3 I decided to read all of the /titles/ in the Artificial Intelligence 3 I decided to read all of the /titles/ in the Artificial Intelligence
4 journal, and found these interesting papers. The entire process took 4 journal, and found these interesting papers. The entire title-reading
5 about 2 hours. 5 process took about 2 hours.
6 6
7 * Interesting Concept 7 * Interesting Concept
8 8
9 Jordi Delgado - Emergence of social conventions in complex networks 9 - (2002) Jordi Delgado - Emergence of social conventions in complex networks
10
11 Here, "social conventions" means a very specific property of graphs
12 in the context of game theory. Their social networks are groups of
13 mindless automotaons which each have a single opinion that can take
14 the values "A" or "B". They use the "coordination game" payoff
15 matrix that engourages each pair of agents to agree with each other,
16 and study various ways the graph can come to 90% of the agents all
17 believe either "A" or "B". It's probably not useful for actual
18 social worlds, and there's no simulation of any interesting
19 environment, but it might be useful for designing protocols, or as a
20 problem solving method.
21
22 References:
23 + L.A. Nunes Amaral, A. Scala, M. Barthélémy, H.E. Stanley, Classes
24 of small-world networks, Proc. Nat. Acad. Sci. 97 (2000)
25 11149–11152.
26 + D.J Watts, S.H. Strogatz, Collective dynamics of small-world
27 networks, Nature 393 (1998) 440–442.
28 + Y. Shoham, M. Tennenholtz, On the emergence of social conventions:
29 Modeling, analysis and simulations, Artificial Intelligence 94
30 (1997) 139–166.
31
32 - (1997) Yoav Shoham, Moshe Tennenholtz - On the emergence of social
33 conventions: modeling, analysis, and simulations
34
10 35
11 Marcelo A. Falappa, Gabriele Kern-Isberner, Guillermo R. Simari - 36 Marcelo A. Falappa, Gabriele Kern-Isberner, Guillermo R. Simari -
12 Explanations, belief revision and defeasible reasoning 37 Explanations, belief revision and defeasible reasoning
13 38
14 Claudio Bettini, X.Sean Wang, Sushil Jajodia - Solving 39 Claudio Bettini, X.Sean Wang, Sushil Jajodia - Solving
64 knowledge discovery in science 89 knowledge discovery in science
65 90
66 Paul Snow - The vulnerability of the transferable belief model to 91 Paul Snow - The vulnerability of the transferable belief model to
67 Dutch books 92 Dutch books
68 93
69 Simon Kasif, Steven Salzberg, David Waltz, John Rachlin, David W. Aha 94 Simon Kasif, Steven Salzberg, David Waltz, John Rachlin, David
70 - A probabilistic framework for memory-based reasoning 95 W. Aha - A probabilistic framework for memory-based reasoning
71 96
72 Geoffrey LaForte, Patrick J. Hayes, Kenneth M. Ford - Why Gödel's 97 Geoffrey LaForte, Patrick J. Hayes, Kenneth M. Ford - Why Gödel's
73 theorem cannot refute computationalism 98 theorem cannot refute computationalism
74 99
75 Hiroshi Motoda, Kenichi Yoshida - Machine learning techniques to make 100 Hiroshi Motoda, Kenichi Yoshida - Machine learning techniques to make
93 Kurt Ammon - An automatic proof of Gödel's incompleteness theorem 118 Kurt Ammon - An automatic proof of Gödel's incompleteness theorem
94 119
95 Shmuel Onn, Moshe Tennenholtz - Determination of social laws for 120 Shmuel Onn, Moshe Tennenholtz - Determination of social laws for
96 multi-agent mobilization 121 multi-agent mobilization
97 122
98 Yoav Shoham, Moshe Tennenholtz - On the emergence of social
99 conventions: modeling, analysis, and simulations
100
101 Stuart J. Russell - Rationality and intelligence 123 Stuart J. Russell - Rationality and intelligence
102 124
103 Hidde de Jong, Arie Rip - The computer revolution in science: steps 125 Hidde de Jong, Arie Rip - The computer revolution in science: steps
104 towards the realization of computer-supported discovery environments 126 towards the realization of computer-supported discovery environments
105 127
148 170
149 John McDermott - R1 (“XCON”) at age 12: lessons from an elementary 171 John McDermott - R1 (“XCON”) at age 12: lessons from an elementary
150 school achiever 172 school achiever
151 173
152 Takeo Kanade - From a real chair to a negative chair 174 Takeo Kanade - From a real chair to a negative chair
153
154 Berthold K.P. Horn, B.G. Schunck - “Determining optical flow”: a
155 retrospective
156 175
157 Harry G. Barrow, J.M. Tenenbaum - Retrospective on “Interpreting line 176 Harry G. Barrow, J.M. Tenenbaum - Retrospective on “Interpreting line
158 drawings as three-dimensional surfaces” 177 drawings as three-dimensional surfaces”
159 178
160 Judea Pearl - Belief networks revisited 179 Judea Pearl - Belief networks revisited
595 Thomas O. Binford - Inferring surfaces from images 614 Thomas O. Binford - Inferring surfaces from images
596 615
597 Larry S. Davis, Azriel Rosenfeld - Cooperating processes for low-level 616 Larry S. Davis, Azriel Rosenfeld - Cooperating processes for low-level
598 vision: A survey 617 vision: A survey
599 618
600 Berthold K.P. Horn, Brian G. Schunck - Determining optical flow 619 - (1980) Berthold K.P. Horn, Brian G. Schunck - Determining optical
620 flow
621
622 Optical flow is an estimation of the movement of brightness
623 patterns. If the image is "smooth" then optical flow is also an
624 estimate of the movement of objects in the image (projected onto the
625 plane of the image). They get some fairly good results on some very
626 contrived examples. Important point is that calculating optical flow
627 involves a relaxation process where the velocities of regions of
628 constant brightness are inferred from the velocities of the edges of
629 those regions.
630
631 This paper is a lead up to Horn's book, Robot Vision.
632
633 Hexagonal sampling may be a good alternative to rectangular
634 sampling.
635
636 A reduced version of this algorithm is implemented in hardware in
637 optical mice to great effect.
638
639 + Hamming, R.W., Numerical Methods for Scientists and Engineers
640 (McGraw-Hill, New York, 1962).
641 + Limb, J.O. and Murphy, J.A., Estimating the velocity of moving
642 images in television signals, Computer Graphics and Image
643 Processing 4 (4) (1975) 311-327.
644 + Mersereau, R.M., The processing of hexagonally sampled
645 two-dimensional signals, Proc. of the IEEE 67 (6) (1979) 930-949.
646
647
648 - (1993) Berthold K.P. Horn, B.G. Schunck - “Determining optical flow”: a
649 retrospective
650
651 Very useful read where Horn criticies his previous paper.
652
653 - Whishes that he distinguished "optical flow" form "motion
654 field". "Optical flow" is an image property, whilc the "motion
655 field" is the movement of objects in 3D space. "Optical flow" is a
656 2D vector field; the "motion field" is 3D.
657 - Wished he made the limitations of his algorithm more clear.
658 - His original paper didn't concern itself with flow segmentation,
659 which is required to interpret real world images with objects and
660 a background.
661 - Thinks that the best thing about the original paper is that it
662 introduced variational calculus methods into computer vision.
663
664 References:
665
666 + R. Courant and D. Hilbert, Methods of Mathematical Physics
667 (Interscience, New York, 1937/1953).
668 + D. Mart, Vision (Freeman, San Francisco, CA, 1982).
669 + C.M. Thompson, Robust photo-topography by fusing
670 shape-from-shading and stereo,Ph.D. Thesis, Mechanical Engineering
671 Department, MIT, Cambridge, MA (1993).
672 + K. Ikeuchi and B.K.P. Horn, Numerical shape from shading and
673 occluding boundaries, Artif lntell. 17 (1981) 141-184.
601 674
602 Katsushi Ikeuchi, Berthold K.P. Horn - Numerical shape from shading 675 Katsushi Ikeuchi, Berthold K.P. Horn - Numerical shape from shading
603 and occluding boundaries 676 and occluding boundaries
604 677
605 Andrew P. Witkin - Recovering surface shape and orientation from 678 Andrew P. Witkin - Recovering surface shape and orientation from
615 688
616 Claude R. Brice, Claude L. Fennema - Scene analysis using regions 689 Claude R. Brice, Claude L. Fennema - Scene analysis using regions
617 690
618 * Cryo! 691 * Cryo!
619 692
620 Kenneth D. Forbus, Peter B. Whalley, John O. Everett, Leo Ureel, Mike 693 - (1999) Kenneth D. Forbus, Peter B. Whalley, John O. Everett, Leo
621 Brokowski, Julie Baher, Sven E. Kuehne - CyclePad: An articulate 694 Ureel, Mike Brokowski, Julie Baher, Sven E. Kuehne - CyclePad: An
622 virtual laboratory for engineering thermodynamics 695 articulate virtual laboratory for engineering thermodynamics
696
697 Should learn about thermodynamics, and about "thermal cycles."
698 http://www.qrg.northwestern.edu/projects/NSF/cyclepad/cyclepad.htm
699
700 This system is more about expressing models and assumtions than
701 automatically generating them, and as such is similiar to our "math
702 language" idea.
703
704 It's like a simple circuit modeller, and similar to Dylan's idea of
705 an online circuit modeler.
706
707 #+begin_quote
708 We found that if CyclePad did not do the “obvious” propagation in
709 preference to interpolation, students trusted it less.
710 #+end_quote
711
712 It's too bad that the paper doesn't mention the shortcommings of the
713 system.
714
715 + J.O. Everett, Topological inference of teleology: Deriving
716 function from structure via evidential reasoning, Artificial
717 Intelligence 113 (1999) 149–202.
718 + P. Hayes, Naive physics 1: Ontology for liquids, in: J. Hobbs,
719 R. Moore (Eds.), Formal Theories of the Commonsense World, Ablex,
720 Norwood, NJ, 1985.
721 + P. Nayak, Automated modeling of physical systems, Ph.D. Thesis,
722 Computer Science Department, Stanford University, 1992.
723 + R.W. Haywood, Analysis of Engineering Cycles: Power, Refrigerating
724 and Gas Liquefaction Plant, Pergamon Press, 1985.
725 + R.M. Stallman, G.J. Sussman, Forward reasoning and
726 dependency-directed backtracking in a system for computer-aided
727 circuit analysis, Artificial Intelligence 9 (1977) 135–196.
728 + Dylan should read this, since it concerns his online circuit
729 analysis idea.
730
731