Sessions of Emergentia

Diner 10 jaar jubileum. Foto's.

Artikelen:

• Wired, Say Hello to Stanley.
• Fox, Thrun, Burgard & Dellaert, Particle filters for mobile robot localization.
• Stanford Racing Team tech paper.

Artikelen:

• Matthijs T. J. Spaan and Nikos Vlassis. Perseus: randomized point-based value iteration for POMDPs. Journal of Artificial Intelligence Research, 2005.

Artikelen:

• Hoofdstuk 5 van Jelle's proefschrift
• Een gerelateerd (maar zeer verschillend) artikel is: Kirby, S. (2000) Syntax without Natural Selection: How compositionality emerges from vocabulary in a population of learners.

Artikelen:

• The manifold ways of perception, Seung & Lee, Science, december 2000.
• Think Globally, Fit Locally: Unsupervised Learning of Low Dimensional Manifolds, Saul & Roweis, JMLR, june 2003.
• Gaussian fields for semi-supervised regression and correspondence learning, Verbeek & Vlassis, submitted.

Artikelen:

• Schyns, Philippe G., Goldstone, Robert L. and Thibaut, Jean-Pierre (1998) THE DEVELOPMENT OF FEATURES IN OBJECT CONCEPTS.
• The Language of Thought Stanford Encyclopedia of Philosophy

Artikelen:

• Probabilistic Logic Learning (DeRaedt en Kersting) (SIGKDD Explorations, 2003)
• Gaertner, Driessens, & Ramon. Graph kernels and Gaussian processes for relational reinforcement learning. ILP '03.
• King et al. Functional genomic hypothesis generation and experimentation by a robot scientist.

Artikelen:

• Michael L. Littman. Markov games as a framework for multi-agent reinforcement learning. In Proceedings of the Eleventh International Conference on Machine Learning, pages 157--163, San Francisco, CA, 1994. Morgan Kaufmann.
• Rational and convergent learning in stochastic games, Michael Bowling and Manuela Veloso. In Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence , pages 1021--1026, Seattle, WA, August 2001.
• Scalable learning in stochastic games, Michael Bowling and Manuela Veloso. In AAAI Workshop on Game Theoretic and Decision Theoretic Agents , Edmonton, Canada, July 2002.

Artikelen:

• Lipshutz, Fodor, Gingeras, & Lockhart. High density synthetic oligonucleotide arrays.
• Tibshirani, Hastie, Narasimhan, & Chu. Diagnosis of multiple cancer types by shrunken centroids of gene expression.
• Storey and Tibshirani. Statistical significance for genomewide studies.

Artikelen:

• Multiagent Planning with Factored MDPs
• Context Specific Multiagent Coordination and Planning with Factored MDPs

Artikelen:

• Peter Dayan. Feudal Q-learning. Technical Report, 1998.
• Thomas G. Dietterich. An overview of MAXQ hierarchical reinforcement learning. In: B.Y. Choueiry and T. Walsh, editors, Proceedings of the Symposium on Abstraction, Reformulation and Approximation (SARA 2000), Lecture Notes in Artificial Intelligence. Springer Verlag, New York, 2000.

Artikelen:

• Christophe Andrieu, Nando de Freitas, Arnaud Doucet en Michael I. Jordan, An introduction to MCMC for Machine Learning, Machine Learning 50, pp. 5-43, 2003.
• Kathryn B. Laskey en James W. Myers, Population Markov Chain Monte Carlo, Machine Learning 50, pp. 175-196, 2003.

Artikelen:

• Universal learning. Hutter: Towards a universal theory of artificial intelligence based on algorithmic probability and sequential decision theory (8p). Wel nogal technisch, maar op z'n minst goed om een indruk te geven van deze benadering.
• Kurzweil. Kurzweil: Red Herring artikel (9p)
• Interview Kurzweil over singularity
• En voor wie meer wil lezen over deze singularity (lang) desgewenst dit artikel
• Emoties. Scheutz, Sloman, Logan: Emotional states and realistic agent behavior (voorstel Marco)
• Scheutz: Computationalism: The Next Generation en ook de 'Epilog' van het boek (voorstel Martijn v O)
• Coevolutie. Hillis: Coevolving Parasites improve simulated evolution as an optimization procedure.
• Ficici: Pareto optimality in coevolutionary learning

Artikelen:

• M. Pelikan, D.E. Goldberg, E. Cantu-Paz: BOA: The Bayesian optimization algorithm
• M. Pelikan, D.E. Goldberg: Escaping hierarchical traps with competent genetic algorithms

Artikelen:

• Solving non-Markovian control tasks with neuroevolution van Faustino Gomez and Risto Miikkulainen, in: Proc. of the Int. Joint Conference on Artificial Intelligence (IJCAI-99, Stockholm, Sweden), 1356-1361. San Francisco, CA:Kaufmann. 1999. (6 pages). Downloadable.
• Efficient reinforcement learning through symbiotic evolution, van David E. Moriarty and Risto Miikkulainen. Machine Learning, 22:11-32, 1996. (23 pages). Downloadable.

• A theoretical model of phase transitions in n hand movements van Haken, Kelso & Hunz,
  Biological Cybernetics, vol. 51, pp. 347-356.
• Mind as motion: explorations in the dics of cognitionvan Van Gelder en Port,
  Hoofdstuk 1.

Artikelen:

• Co-evolution in the successful learning ofkgammon strategy van Pollack en Blair,
  downloadable, 21 pp.
• Co-evolution to the edge of chaos: coupled fitness landscapes, poised states, and co-evolutionary avalanchesvan Kauffman en Johnsen,
  Artificial Life II, 45 pp.
• Incremental self-improvement for life-time multi-agent rercement learning van Jieyu Zhao en Juergen Schmidhuber,
  Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior (SAB'96), pp. 516-525, Cape Cod, USA, 1996. Ook downloadable.

Artikelen:

• Neural networks and the bias/variance dilemma van S. Geman, E. Bienenstock en R. Doursat,
  Neural Computation 4, 1992, pp. 1-58.
• On bias, variance, 0/1 loss and the curf-dimensionality van J.H. Friedman,
  Data Mining and Knowledge Discovery 1(1), 1997, pp. 55-77.

Zie voor het laatste paper en meer deze website.

Artikelen:

• Computational and dynamical languages for autonomous agents van R.D. Beer,
  uit: Port and Van Gelder (eds.), Mind as motion. Explorations in the dynamics of cognition, pp. 121-147, MIT Press, Cambridge, MA, 1995.
• Analysis of dynamical recognizers van Blair, A.D. and Pollack, J.B.
  Neural Computation 9(5), 1997, pp. 1127-1142.
• Analysis of the hidden units in layered networks trained to classify sonar targets van Gorman, R.P. and Sejnowski, T.J.,
  Neural Networks 1, 1988, pp. 75-89.

Artikelen:

• A learning algorithm for Boltzmann Machines van David H.Ackley, Geoffrey E.Hinton en Terrence J. Sejnowski,
  Cognitive Science 9, pp. 147 -169, 1985
• Deterministic Learning Rules for Boltzmann Machines van Hilbert J. Kappen, Neural Networks, vol.8, no.4, 537-548.
  PostScript [compress, 174 Kb] [zip, 120 Kb]

Artikelen:

• Finding structure in time van J.L. Elman,
  Cognitive Science 14, pp. 179 -211, 1990
• Adaptive state representation and estimation using recurrent neural networks van R.J. Williams,
  uit: T. Miller, R.S. Sutton and P. Werbos (eds.), Neural networks for control, MIT Press, Cambridge, MA, 1990.
  PostScript [gzip, 47 Kb] [zip, 47 Kb]

Artikelen:
Stukjes uit:

• Computing machinery and intelligence van A.M. Turing
  GIF [1, 28 Kb] [2, 51 Kb] [3, 75 Kb]
• The Mind's I van Daniel Dennet
  GIF [1, 93 Kb]
• The society of mind van Marvin Minsky
  GIF [1, 35 Kb]
• The sciences of the artificial van Herb Simon
  GIF [1, 37 Kb] [2, 42 Kb] [3, 50 Kb] [4, 49 Kb] [5, 48 Kb]
• Artificial Intelligence van Patrick Henry Winston en
  Unified theories of cognition van Alan Newell
  GIF [1, 53 Kb] [2, 38 Kb]
• The origins of intelligence van Luc Steels

Voor een pagina met al de bovengenoemde stukken, klik hier. Voor een samenvatting van het besproken klik hier.

Artikelen:

• Restricted attentional capacity within but not between sensory modalities van J. Duncan, S. Martens en R. Ward, Nature, 387, 1997, pp. 808-810
• Interference in attention within and between perceptual modalities, Doctoraalscriptie Cognitiewetenschap KUN van Sander Martens
• In a blink of the mind's eye van J.M. Wolfe, Nature, 387, 756-757, 1997

Artikelen:

• Bayesian methods for neural networks van Chris Bishop [PostScript, 310 Kb]
• Bayesian non-linear modelling with neural networks van David MacKay [PostScript, 1.7 Mb]
• Neural networks van Michael Jordan en Chris Bishop [PostScript, 360 Kb]

Voor meer papers en links klik hier.

Artikelen:

• Biologically plausible reinforcement learning in multi-layer neural networks van Bram Bakker
• A possible link between artificial and biological neural network learning rules, H. Zhu, Santa Fe Institute
• Learning by statistical cooperation of self-interested neuron-like computing elements van A.G. Barto, Human Neurobiology (1985) vol. 4 pp. 229-256

Artikelen:

• Data exploration using self-organizing maps (pp. 20-30) van Samuel Kaski
• Een stuk uit Self-organizing maps (pp. 160-173) van Teuvo Kohonen
• Modeling psychological stereotypes in self-organizing maps van T. Cramer, J. Goppert en W. Rosenstiel, uit de proceedings van de ICANN '96.

Artikelen:

• Reinforcement Learning: A Survey van Leslie Pack Kaelbling et.al., te vinden op http://www.cs.brown.edu/people/lpk/home.html#publications
• Learning to Predict by the Methods of Temporal Differences van Rich Sutton, te vinden op ftp://ftp.cs.umass.edu/pub/anw/pub/sutton/sutton-88.ps.gz

Artikelen:

• A comparison of Q-learning and classifier systems van M. Dorigo en H. Bersini, in Proc. of ... from animals to animats, 3rd Int. Conf. on Simulation of Adaptive Behavior, 1994. Te vinden op http://iridia.ulb.ac.be/dorigo/publications.html onder internationale conferenties.
• Een overzicht over machine learning uit een speciale encyclopedie. Het bespreekt verschillende methoden voor machine learning, zoals ID3.

Artikelen:

• Uit The evolution of cooperation van Axelrod: hoofdstuk 1 en evt. 2 of 5
• Uit The role of behavior in evolution van H.C. Plotkin (1988): hoofdstuk 5, Learning & evolution
• Uit Evolution of human language van J. Hurford (ed.) (1997): Steels, L. (1996), Synthesising the origins of language and meaning using co-evolution, self-organisation and level formation. Te vinden op http://arti.vub.ac.be/www/steels/edin.ps of (korter) op: http://arti.vub.ac.be/www/krest/robot/alife4.ps

Artikelen:

• What is it like to be a bat? van Thomas Nagel en een review, uit The Mind's I
• Een artikel over bewustzijn door Koch en Crick in de SCAM (nr. 3 uit 1992).

Artikelen:

• The recent excitement about neural networks van Crick
• Uit The principles of neural science van Kandel Schwartz en Jessell: Anatomical organization of the nervous system door Kelly en Dodd
• Een stukje van Kandel en Hawkins uit de Scientific American: The biological basis of learning and individuality

Reactie: Etzioni, O., Intelligence without Robots: A Reply to Brooks, AI Magazine 14 no. 4 (winter '93).