#+title:Interesting Papers in Artificial Intelligence

 #+author: Robert McIntyre

 #+email: rlm@mit.edu

 #+setupfile: ../../aurellem/org/setup.org

 #+include: ../../aurellem/org/level-0.org

 

 I decided to read all of the /titles/ in the Artificial Intelligence

 journal, and found these interesting papers.  The entire title-reading

 process took about 2 hours.

 

 * Interesting Concept

 

 - (2002) Jordi Delgado - Emergence of social conventions in complex networks

  

   Here, "social conventions" means a very specific property of graphs

   in the context of game theory. Their social networks are groups of

   mindless automotaons which each have a single opinion that can take

   the values "A" or "B". They use the "coordination game" payoff

   matrix that engourages each pair of agents to agree with each other,

   and study various ways the graph can come to 90% of the agents all

   believe either "A" or "B".  It's probably not useful for actual

   social worlds, and there's no simulation of any interesting

   environment, but it might be useful for designing protocols, or as a

   problem solving method.

 

   References: 

   + L.A. Nunes Amaral, A. Scala, M. Barthélémy, H.E. Stanley, Classes

     of small-world networks, Proc. Nat. Acad. Sci. 97 (2000)

     11149–11152.

   + D.J Watts, S.H. Strogatz, Collective dynamics of small-world

     networks, Nature 393 (1998) 440–442.

   + Y. Shoham, M. Tennenholtz, On the emergence of social conventions:

     Modeling, analysis and simulations, Artificial Intelligence 94

     (1997) 139–166.

 

 - (1997) Yoav Shoham, Moshe Tennenholtz - On the emergence of social

   conventions: modeling, analysis, and simulations

 

 

 Marcelo A. Falappa, Gabriele Kern-Isberner, Guillermo R. Simari -

 Explanations, belief revision and defeasible reasoning

 

 Claudio Bettini, X.Sean Wang, Sushil Jajodia - Solving

 multi-granularity temporal constraint networks

 

 Alberto Maria Segre, Sean Forman, Giovanni Resta, Andrew Wildenberg -

 Nagging: A scalable fault-tolerant paradigm for distributed search

 

 Fahiem Bacchus, Xinguang Chen, Peter van Beek, Toby Walsh - Binary

 vs. non-binary constraints

 

 Jie Cheng, Russell Greiner, Jonathan Kelly, David Bell, Weiru Liu -

 Learning Bayesian networks from data: An information-theory based

 approach

 

 Kurt Engesser, Dov M. Gabbay - Quantum logic, Hilbert space, revision

 theory

 

 J.-D. Fouks, L. Signac - The problem of survival from an algorithmic

 point of view

 

 Catherine Carr - The MIT Encyclopedia of the Cognitive Sciences,

 edited by Robert Wilson and Frank Keil

 

 - Tim Taylor - Christoph Adami, Introduction to Artificial Life

   References:

   + M.A. Boden (Ed.), The Philosophy of Artificial Life, Oxford

     University Press, Oxford, 1996.

   + C.G. Langton (Ed.), Artificial Life: An Introduction, MIT Press,

     Cambridge, MA, 1995.    

 

 A.S d'Avila Garcez, K Broda, D.M Gabbay - Symbolic knowledge

 extraction from trained neural networks: A sound approach

 

 José Hernández-Orallo - Truth from Trash. How Learning Makes Sense by

 Chris Thornton

 

 Fabio G. Cozman - Credal networks

 

 Aaron N. Kaplan, Lenhart K. Schubert - A computational model of belief

 

 Mike Perkowitz, Oren Etzioni - Towards adaptive Web sites: Conceptual

 framework and case study

 

 Wilhelm Rödder - Conditional logic and the Principle of Entropy

 

 Christian Vilhelm, Pierre Ravaux, Daniel Calvelo, Alexandre Jaborska,

 Marie-Christine Chambrin, Michel Boniface - Think!: A unified

 numerical–symbolic knowledge representation scheme and reasoning

 system

 

 Charles L. Ortiz Jr. - A commonsense language for reasoning about

 causation and rational action

 

 Raúl E. Valdés-Pérez - Principles of human—computer collaboration for

 knowledge discovery in science

 

 Paul Snow - The vulnerability of the transferable belief model to

 Dutch books

 

 Simon Kasif, Steven Salzberg, David Waltz, John Rachlin, David

 W. Aha - A probabilistic framework for memory-based reasoning

 

 Geoffrey LaForte, Patrick J. Hayes, Kenneth M. Ford - Why Gödel's

 theorem cannot refute computationalism

 

 Hiroshi Motoda, Kenichi Yoshida - Machine learning techniques to make

 computers easier to use

 

 Aravind K. Joshi - Role of constrained computational systems in

 natural language processing

 

 Moshe Tennenholtz - On stable social laws and qualitative equilibria

 

 Michael Arbib - The metaphorical brains

 

 Andrew Gelsey, Mark Schwabacher, Don Smith - Using modeling knowledge

 to guide design space search

 

 Márk Jelasity, József Dombi - GAS, a concept on modeling species in

 genetic algorithms

 

 Randall H. Wilson - Geometric reasoning about assembly tools

 

 Kurt Ammon - An automatic proof of Gödel's incompleteness theorem

 

 Shmuel Onn, Moshe Tennenholtz - Determination of social laws for

 multi-agent mobilization

 

 Stuart J. Russell - Rationality and intelligence

 

 Hidde de Jong, Arie Rip - The computer revolution in science: steps

 towards the realization of computer-supported discovery environments

 

 Adnan Darwiche, Judea Pearl - On the logic of iterated belief revision

 

 R.C. Holte, T. Mkadmi, R.M. Zimmer, A.J. MacDonald - Speeding up

 problem solving by abstraction: a graph oriented approach

 

 R. Holte, T. Mkadmi, R.M. Zimmer, A.J. McDonald - Speeding up problem

 solving by abstraction: a graph oriented approach

 

 Raúl E. Valdés-Pérez - A new theorem in particle physics enabled by

 machine discovery

 

 Dan Roth - On the hardness of approximate reasoning

 

 Bart Selman, David G. Mitchell, Hector J. Levesque - Generating hard

 satisfiability problems

 

 Herbert A. Simon - Artificial intelligence: an empirical science

 

 John K. Tsotsos - Behaviorist intelligence and the scaling problem

 

 Shigeki Goto, Hisao Nojima - Equilibrium analysis of the distribution

 of information in human society

 

 Raúl E. Valdés-Pérez - Machine discovery in chemistry: new results

 

 Stephen W. Smoliar - Artificial life: Christopher G. Langton, ed.

 

 Yoav Shoham, Moshe Tennenholtz - On social laws for artificial agent

 societies: off-line design

 

 Barbara Hayes-Roth - An architecture for adaptive intelligent systems

 

 Bruce Randall Donald - On information invariants in robotics

 

 Ian P. Gent, Toby Walsh - Easy problems are sometimes hard

 

 Tad Hogg, Colin P. Williams - The hardest constraint problems: A

 double phase transition

 

 Yoram Moses, Yoav Shoham - Belief as defeasible knowledge

 

 Donald Michie - Turing's test and conscious thought

 

 John McDermott - R1 (“XCON”) at age 12: lessons from an elementary

 school achiever

 

 Takeo Kanade - From a real chair to a negative chair

 

 Harry G. Barrow, J.M. Tenenbaum - Retrospective on “Interpreting line

 drawings as three-dimensional surfaces”

 

 Judea Pearl - Belief networks revisited

 

 Glenn A. Kramer - A geometric constraint engine

 

 Fausto Giunchiglia, Toby Walsh - A theory of abstraction

 

 John L. Pollock - How to reason defeasibly

 

 Aaron Sloman - The emperor's real mind: Review of Roger Penrose's the

 emperor's new mind: Concerning computers, minds and the laws of

 physics

 

 Olivier Dordan - Mathematical problems arising in qualitative

 simulation of a differential equation

 

 Eric Saund - Putting knowledge into a visual shape representation

 

 Michael Freund, Daniel Lehmann, Paul Morris - Rationality,

 transitivity, and contraposition

 

 Anthony S. Maida - Maintaining mental models of agents who have

 existential misconceptions

 

 Henry A. Kautz, Bart Selman - Hard problems for simple default logics

 

 Mark J. Stefik, Stephen Smoliar - Four reviews of The Society of Mind

 and a response

 

 Michael G. Dyer - A society of ideas on cognition: Review of Marvin

 Minsky's The Society of Mind

 

 Matthew Ginsberg - The society of mind: Marvin Minsky

 

 George N. Reeke Jr - The society of mind: Marvin Minsky

 

 Stephen W. Smoliar - The society of mind: Marvin Minsky

 

 Marvin Minsky - Society of mind: A response to four reviews

 

 Stephen W. Smoliar - How to build a person: A prolegomenon: John

 Pollock

 

 David Makinson, Karl Schlechta - Floating conclusions and zombie

 paths: Two deep difficulties in the “directly skeptical” approach to

 defeasible inheritance nets

 

 Donald A. Norman - Approaches to the study of intelligence

 

 Rodney A. Brooks - Intelligence without representation

 

 David Kirsh - Today the earwig, tomorrow man?

 

 Douglas B. Lenat, Edward A. Feigenbaum - On the thresholds of

 knowledge

 

 Jordan B. Pollack - Recursive distributed representations

 

 R. Bhaskar, Anil Nigam - Qualitative physics using dimensional

 analysis

 

 Don F. Beal - A generalised quiescence search algorithm

 

 Kai-Fu Lee, Sanjoy Mahajan - The development of a world class Othello

 program

 

 Helmut Horacek - Reasoning with uncertainty in computer chess

 

 Jeff Shrager - Induction: Process of inference, learning and

 discovery: John H. Holland, Keith J. Holyoak, Richard E. Nisbett, and

 Paul R. Thagard (MIT Press, Cambridge, MA, 1986); 355 pages

 

 Daniel S. Weld - The psychology of everyday things: Donald A. Norman,

 (Basic Books, New York, 1988); 257 pages, $19.95

 

 John R. Anderson - A theory of the origins of human knowledge

 

 G. Tesauro, T.J. Sejnowski - A parallel network that learns to play

 backgammon

 

 G. Priest - Reasoning about truth

 

 Donald Perlis - Truth and meaning

 

 Daniel S. Weld - Women, fire, and dangerous things: George Lakoff,

 (University of Chicago Press, Chicago, IL, 1987); 614 pages, $29.95

 

 Mark J. Stefik - On book reviews policy and process

 

 Robert K. Lindsay - The science of the mind: Owen J. Flanagan, Jr.,

 (MIT Press, Cambridge, MA, 1984); 290 pages

 

 Sheila Rock - On machine intelligence: Donald Michie, 2nd ed. (Ellis

 Horwood, Chichester, United Kingdom, 1986); 265 pages, £29.95

 

 Stephen W. Smoliar - Epistemology and cognition: A.I. Goldman,

 (Harvard University Press, Cambridge, MA, 1986); ix + 437 pages,

 $27.50

 

 David Elliot Shaw - On the range of applicability of an artificial

 intelligence machine

 

 Michael Gordon - Machine intelligence and related topics: An

 information scientist's weekend book: Donald Michie, (Gordon and

 Breach, New York, 1982); 328 pages, $57.75

 

 Ryszard S. Michalski, Patrick H. Winston - Variable precision logic

 

 Martin Herman, Takeo Kanade - Incremental reconstruction of 3D scenes

 from multiple, complex images

 

 vision : June 8–11, 1987, London, United Kingdom

 

 André Vellino - Artificial intelligence: The very idea: J. Haugeland,

 (MIT Press, Cambridge, MA, 1985); 287 pp.

 

 Judea Pearl - Fusion, propagation, and structuring in belief networks

 

 Daniel G. Bobrow - Scientific debate

 

 Mark Stefik - The AI business: Commercial uses of artificial

 intelligence: P.H. Winston and K.A. Prendergast, (MIT Press,

 Cambridge, MA 1984); 324 pages, $15.95

 

 Hans Berliner, Carl Ebeling - The SUPREM architecture: A new

 intelligent paradigm

 

 Donna Reese - Artificial intelligence: P.H. Winston, (Addison-Wesley,

 Reading, MA, 2nd ed., 1984); 527 pages

 

 Kenneth D. Forbus - Structure and interpretation of computer programs:

 H. Abelson and G.J. Sussman with J. Sussman, (MIT, Cambridge, 1985);

 503 pages

 

 Chia-Hoang Lee, Azriel Rosenfeld - Improved methods of estimating

 shape from shading using the light source coordinate system

 

 Daniel G. Bobrow, Patrick J. Hayes - Artificial intelligence — Where

 are we?

 

 Barbara J. Grosz - Natural-language processing

 

 Johan De Kleer - How circuits work

 

 G.D. Ritchie, F.K. Hanna - am: A case study in AI methodology

 

 Douglas B. Lenat, John Seely Brown - Why am and eurisko appear to work

 

 Elaine Kant - On the efficient synthesis of efficient programs

 

 Randall Davis, Reid G. Smith - Negotiation as a metaphor for

 distributed problem solving

 

 Patrick H. Winston - Learning new principles from precedents and

 exercises

 

 Paul S. Rosenbloom - A world-championship-level Othello program

 

 Tomas Lozano-Perez - Robotics

 

 Tom M. Mitchell - Generalization as search

 

 Dana S. Nau - The last player theorem

 

 Hans J. Berliner - Backgammon computer program beats world champion

 

 Gerald Jay Sussman, Guy Lewis Steele Jr. - Constraints—A language for

 expressing almost-hierarchical descriptions

 

 Takeo Kanade - A theory of Origami world

 

 Ria Follett - Synthesising recursive functions with side effects

 

 John McCarthy - Circumscription—A form of non-monotonic reasoning

 

 Michael A. Bauer - Programming by examples

 

 Patrick H. Winston - Learning by creatifying transfer frames

 

 Alan Bundy - Will it reach the top? Prediction in the mechanics world

 

 Richard M. Stallman, Gerald J. Sussman - Forward reasoning and

 dependency-directed backtracking in a system for computer-aided

 circuit analysis

 

 D. Marr - Artificial intelligence—A personal view

 

 Berthold K.P. Horn - Understanding image intensities

 

 F. Malloy Brown - Doing arithmetic without diagrams

 

 Azriel Rosenfeld - The psychology of computer vision: Patrick Henry

 Winston (ed.) McGraw-Hill, New York, 1975, vi+282 pages, $19.50

 

 R.C.T. Lee - On machine intelligence: D. Michie. Halstead Press, a

 division of John Wiley & Sons, 1974.

 

 W.W. Bledsoe, Peter Bruell - A man-machine theorem-proving system

 

 Gary G. Hendrix - Modeling simultaneous actions and continuous

 processes

 

 Yoshiaki Shirai - A context sensitive line finder for recognition of

 polyhedra

 

 Kenneth Mark Colby, Franklin Dennis Hilf, Sylvia Weber, Helena C

 Kraemer - Turing-like indistinguishability tests for the validation of

 a computer simulation of paranoid processes

 

 Aaron Sloman - Interactions between philosophy and artificial

 intelligence: The role of intuition and non-logical reasoning in

 intelligence

 

 * Story related

 

 Charles B. Callaway, James C. Lester - Narrative prose generation

 

 - Katja Markert, Udo Hahn :: Understanding metonymies in discourse

      Metonymies are difficult enough to drive these people to use the

      context of the sentences around the metonymy to interpret

      it. They create a set of heuristics which interpret

      metonomies. The first is obvious violations of sentence rules,

      such as having a non-agent do something only an agent can do.

 

      Another rule is that metonomyies should be more "apt", where it's

      more likely for a T.V. Screen to refer to the T.V. than a small

      button on the T.V., or a transistor. 

 

      Metonymies should be very difficult for current parsers to

      understand, and are good examples, since they are short and

      require context and common sense.

 

      They have a dumb, ad-hoc "common sense database" that is

      dissapointing. It contains subclasses and has-a relations.

 

      References:

      + D.A. Cruse, On the transitivity of the part-whole relation,

        J. Linguistics 15 (1979) 29–38.

        good quotes:

        - We took the door off its hinges and went through it.

        - The house has a handle.sources 

 

 

 Kathleen R. McKeown, Steven K. Feiner, Mukesh Dalal, Shih-Fu Chang -

 Generating multimedia briefings: coordinating language and

 illustration

 

 Varol Akman - Formalizing common sense: Papers by John McCarthy:

 V. Lifschitz, ed., (Ablex Publishing Corporation, Norwood, NJ, 1990);

 vi+256 pages, hardback, ISBN 0-89391-535-1 (Library of Congress:

 Q335.M38 1989)

 

 Akira Shimaya - Interpreting non-3-D line drawings

 

 Adam J. Grove - Naming and identity in epistemic logic part II: a

 first-order logic for naming

 

 Luc Lismont, Philippe Mongin - A non-minimal but very weak

 axiomatization of common belief

 

 on integration of natural language and vision processing

 

 Russell Greiner - Learning by understanding analogies

 

 * Review Articles

 

 H.Jaap van den Herik, Jos W.H.M. Uiterwijk, Jack van Rijswijck - Games

 solved: Now and in the future

 

 Jonathan Schaeffer, H.Jaap van den Herik - Games, computers, and

 artificial intelligence

 

 Peter A. Flach - On the state of the art in machine learning: A

 personal review

 

 A.G. Cohn, D. Perlis - “Field Reviews”: A new style of review article

 for Artificial Intelligence

 

 James Delgrande, Arvind Gupta, Tim Van Allen - A comparison of

 point-based approaches to qualitative temporal reasoning

 

 Weixiong Zhang, Rina Dechter, Richard E. Korf - Heuristic search in

 artificial intelligence

 

 Karen Sparck Jones - Information retrieval and artificial intelligence

 

 Wolfram Burgard, Armin B. Cremers, Dieter Fox, Dirk Hähnel, Gerhard

 Lakemeyer, Dirk Schulz, Walter Steiner, Sebastian Thrun - Experiences

 with an interactive museum tour-guide robot

 

 Minoru Asada, Hiroaki Kitano, Itsuki Noda, Manuela Veloso - RoboCup:

 Today and tomorrow—What we have learned

 

 Margaret A. Boden - Creativity and artificial intelligence

 

 Daniel G. Bobrow, J.Michael Brady - Artificial Intelligence 40 years

 later

 

 Fangzhen Lin, Hector J. Levesque - What robots can do: robot programs

 and effective achievability

 

 Melanie Mitchell - L.D. Davis, handbook of genetic algorithms

 

 Russell Greiner, Adam J. Grove, Alexander Kogan - Knowing what doesn't

 matter: exploiting the omission of irrelevant data

 

 W. Whitney, S. Rana, J. Dzubera, K.E. Mathias - Evaluating

 evolutionary algorithms

 

 David S. Touretzky - Neural networks in artificial intelligence:

 Matthew Zeidenberg

 

 Mark J. Stefik, Stephen W. Smoliar - The commonsense reviews

 

 Peter Szolovits, Stephen G. Pauker - Categorical and probabilistic

 reasoning in medicine revisited

 

 Daniel G. Bobrow - Artificial intelligence in perspective: a

 retrospective on fifty volumes of the Artificial Intelligence Journal

 

 David Kirsh - Foundations of AI: The big issues

 

 Hector J. Levesque - All I know: A study in autoepistemic logic

 

 J.T. Schwartz, M. Sharir - A survey of motion planning and related

 geometric algorithms

 

 Larry S. Davis, Azriel Rosenfeld - Cooperating processes for low-level

 vision: A survey

 

 Hans J. Berliner - A chronology of computer chess and its literature

 

 John McCarthy - Artificial intelligence: a paper symposium: Professor

 Sir James Lighthill, FRS. Artificial Intelligence: A General

 Survey. In: Science Research Council, 1973

 * Cortex related (sensory fusion / simulated worlds)

 

 Alfonso Gerevini, Jochen Renz - Combining topological and size

 information for spatial reasoning

 

 John Slaney, Sylvie Thiébaux - Blocks World revisited

 

 Wai K. Yeap, Margaret E. Jefferies - Computing a representation of the

 local environment

 

 R.P. Loui - On the origin of objects: B.C. Smith's MIT Press,

 Cambridge, MA, 1996. $37.50 (cloth). $17.50 (paper). 440 pages. ISBN

 0-262-69209-0

 

 Tze Yun Leong - Multiple perspective dynamic decision making

 

 Cristiano Castelfranchi - Modelling social action for AI agents

 

 Luc Steels - The origins of syntax in visually grounded robotic agents

 

 Sebastian Thrun - Learning metric-topological maps for indoor mobile

 robot navigation

 

 John Haugeland - Body and world: a review of What Computers Still

 Can't Do: A critique of artificial reason (Hubert L. Dreyfus): (MIT

 Press, Cambridge, MA, 1992); liii + 354 pages, $13.95

 

 David J. Musliner, Edmund H. Durfee, Kang G. Shin - World modeling for

 the dynamic construction of real-time control plans

 

 Jozsef A. Toth - Reasoning agents in a dynamic world: The frame

 problem: Kenneth M. Ford and Patrick J. Hayes, eds., (JAI Press,

 Greenwich, CT, 1991); 290+xiv pages

 

 Michael A. Arbib, Jim-Shih Liaw - Sensorimotor transformations in the

 worlds of frogs and robots

 

 Ingemar J. Cox, John J. Leonard - Modeling a dynamic environment using

 a Bayesian multiple hypothesis approach

 

 on integration of natural language and vision processing

 

 Demetri Terzopoulos, Andrew Witkin, Michael Kass - Constraints on

 deformable models:Recovering 3D shape and nonrigid motion

 

 Bruce R. Donald - A search algorithm for motion planning with six

 degrees of freedom

 

 Yorick Wilks - Making preferences more active

 

 * Vision Related

 

 Azriel Rosenfeld - B. Jähne, H. Haussecker, and P. Geissler, eds.,

 Handbook of Computer Vision and Applications. 1. Sensors and

 Imaging. 2. Signal Processing and Pattern Recognition. 3. Systems and

 Applications

 

 Thomas F. Stahovich, Randall Davis, Howard Shrobe - Qualitative

 rigid-body mechanics

 

 Tzachi Dar, Leo Joskowicz, Ehud Rivlin - Understanding mechanical

 motion: From images to behaviors

 

 Minoru Asada, Eiji Uchibe, Koh Hosoda - Cooperative behavior

 acquisition for mobile robots in dynamically changing real worlds via

 vision-based reinforcement learning and development

 

 Thomas F. Stahovich, Randall Davis, Howard Shrobe - Generating

 multiple new designs from a sketch

 

 Ernst D. Dickmanns - Vehicles capable of dynamic vision: a new breed

 of technical beings?

 

 Thomas G. Dietterich, Richard H. Lathrop, Tomás Lozano-Pérez - Solving

 the multiple instance problem with axis-parallel rectangles

 

 Rajesh P.N. Rao, Dana H. Ballard - An active vision architecture based

 on iconic representations

 

 John K. Tsotsos, Scan M. Culhane, Winky Yan Kei Wai, Yuzhong Lai, Neal

 Davis, Fernando Nuflo - Modeling visual attention via selective tuning

 

 Roger Mohr, Boubakeur Boufama, Pascal Brand - Understanding

 positioning from multiple images

 

 Andrew Zisserman, David Forsyth, Joseph Mundy, Charlie Rothwell, Jane

 Liu, Nic Pillow - 3D object recognition using invariance

 

 Naresh C. Gupta, Laveen N. Kanal - 3-D motion estimation from motion

 field

 

 Damian M. Lyons - Vision, instruction, and action: David Chapman, (MIT

 Press Cambridge, MA, 1991); 295 pages, $35.00, (paperback)

 

 Yoshinori Suganuma - Learning structures of visual patterns from

 single instances

 

 Dana H. Ballard - Animate vision

 

 Raymond Reiter, Alan K. Mackworth - A logical framework for depiction

 and image interpretation

 

 Ellen Lowenfeld Walker, Martin Herman - Geometric reasoning for

 constructing 3D scene descriptions from images

 

 Michele Barry, David Cyrluk, Deepak Kapur, Joseph Mundy, Van-Duc

 Nguyen - A multi-level geometric reasoning system for vision

 

 Alex P. Pentland - Shading into texture

 

 Brady - Parallelism in Vision

 

 Jon A. Webb, J.K. Aggarwal - Structure from motion of rigid and

 jointed objects

 

 Michael Brady - Computer vision

 

 Takeo Kanade - Recovery of the three-dimensional shape of an object

 from a single view

 

 Rodney A. Brooks - Symbolic reasoning among 3-D models and 2-D images

 

 H.K. Nishihara - Intensity, visible-surface, and volumetric

 representations

 

 Thomas O. Binford - Inferring surfaces from images

 

 Larry S. Davis, Azriel Rosenfeld - Cooperating processes for low-level

 vision: A survey

 

 - (1980) Berthold K.P. Horn, Brian G. Schunck - Determining optical

   flow

 

   Optical flow is an estimation of the movement of brightness

   patterns. If the image is "smooth" then optical flow is also an

   estimate of the movement of objects in the image (projected onto the

   plane of the image). They get some fairly good results on some very

   contrived examples. Important point is that calculating optical flow

   involves a relaxation process where the velocities of regions of

   constant brightness are inferred from the velocities of the edges of

   those regions.

   

   This paper is a lead up to Horn's book, Robot Vision.

 

   Hexagonal sampling may be a good alternative to rectangular

   sampling.

 

   A reduced version of this algorithm is implemented in hardware in

   optical mice to great effect.

 

   + Hamming, R.W., Numerical Methods for Scientists and Engineers

     (McGraw-Hill, New York, 1962).

   + Limb, J.O. and Murphy, J.A., Estimating the velocity of moving

     images in television signals, Computer Graphics and Image

     Processing 4 (4) (1975) 311-327.

   + Mersereau, R.M., The processing of hexagonally sampled

     two-dimensional signals, Proc. of the IEEE 67 (6) (1979) 930-949.

 

 

 - (1993) Berthold K.P. Horn, B.G. Schunck - “Determining optical flow”: a

   retrospective

   

   Very useful read where Horn criticies his previous paper.

 

   - Whishes that he distinguished "optical flow" form "motion

     field". "Optical flow" is an image property, whilc the "motion

     field" is the movement of objects in 3D space. "Optical flow" is a

     2D vector field; the "motion field" is 3D.

   - Wished he made the limitations of his algorithm more clear.

   - His original paper didn't concern itself with flow segmentation,

     which is required to interpret real world images with objects and

     a background.

   - Thinks that the best thing about the original paper is that it

     introduced variational calculus methods into computer vision.

     

   References:

 

   + R. Courant and D. Hilbert, Methods of Mathematical Physics

     (Interscience, New York, 1937/1953).

   + D. Mart, Vision (Freeman, San Francisco, CA, 1982).

   + C.M. Thompson, Robust photo-topography by fusing

     shape-from-shading and stereo,Ph.D. Thesis, Mechanical Engineering

     Department, MIT, Cambridge, MA (1993).

   + K. Ikeuchi and B.K.P. Horn, Numerical shape from shading and

     occluding boundaries, Artif lntell. 17 (1981) 141-184.

 

 Katsushi Ikeuchi, Berthold K.P. Horn - Numerical shape from shading

 and occluding boundaries

 

 Andrew P. Witkin - Recovering surface shape and orientation from

 texture

 

 Irwin Sobel - On calibrating computer controlled cameras for

 perceiving 3-D scenes

 

 P.M. Will, K.S. Pennington - Grid coding: A preprocessing technique

 for robot and machine vision

 

 M.B. Clowes - On seeing things

 

 Claude R. Brice, Claude L. Fennema - Scene analysis using regions

 

 * Cryo!

 

 - (1999) Kenneth D. Forbus, Peter B. Whalley, John O. Everett, Leo

   Ureel, Mike Brokowski, Julie Baher, Sven E. Kuehne - CyclePad: An

   articulate virtual laboratory for engineering thermodynamics

      

   Should learn about thermodynamics, and about "thermal cycles."

   http://www.qrg.northwestern.edu/projects/NSF/cyclepad/cyclepad.htm

   

   This system is more about expressing models and assumtions than

   automatically generating them, and as such is similiar to our "math

   language" idea.

 

   It's like a simple circuit modeller, and similar to Dylan's idea of

   an online circuit modeler.

   

   #+begin_quote

   We found that if CyclePad did not do the “obvious” propagation in

   preference to interpolation, students trusted it less.

   #+end_quote

   

   It's too bad that the paper doesn't mention the shortcommings of the

   system. 

   

   + J.O. Everett, Topological inference of teleology: Deriving    

     function from structure via evidential reasoning, Artificial

     Intelligence 113 (1999) 149–202.

   + P. Hayes, Naive physics 1: Ontology for liquids, in: J. Hobbs,

     R. Moore (Eds.), Formal Theories of the Commonsense World, Ablex,

     Norwood, NJ, 1985.

   + P. Nayak, Automated modeling of physical systems, Ph.D. Thesis,

     Computer Science Department, Stanford University, 1992.

   + R.W. Haywood, Analysis of Engineering Cycles: Power, Refrigerating

     and Gas Liquefaction Plant, Pergamon Press, 1985.

   + R.M. Stallman, G.J. Sussman, Forward reasoning and

     dependency-directed backtracking in a system for computer-aided

     circuit analysis, Artificial Intelligence 9 (1977) 135–196.

     + Dylan should read this, since it concerns his online circuit

       analysis idea.