Abstract
The deep formal and conceptual link existing between artificial life and artificial intelligence can be highlighted using conceptual tools derived by Karl Popper's evolutionary epistemology.
Starting from the observation that the structure itself of an organism embodies knowledge about the environment which it is adapted to, it is possible to regard evolution as a learning process. This process is subject to the same rules indicated by Popper for the growth of scientific knowledge: causal conjectures (mutations) and successive refutations (extinction). In the field of machine learning such a paradigm is represented by genetic algorithms that, simulating biological processes, emulate cognitive processes. From a practical viewpoint, that perspective allows to identify the two different kinds of learning considered by artificial intelligence, knowledge acquisition and skill improvement, and to get a different view of the problem of heuristic knowledge in learning systems. From a theoretical point of view, these considerations can shade a new light on an old epistemological problem: why do we live in a learnable world?
Similar content being viewed by others
Bibliography
R. Ashby,Design for a brain, London, Chapman and Hall, 1952.
J. Barrow,The world within the world, Oxford, Oxford University Press, 1988.
R.K. Belew, “Un ruolo per la scienza dei calcolatori nella vita artificiale”,Sistemi intelligenti 2, 1992, 319–327.
J.T. Bonner,The evolution of complexity by means of natural selection, Princeton, Princeton University Press, 1988.
D. Campbell, “Evolutionary epistemology”, in [Schilpp 1980].
P.C.W. Davies, “Why is the physical world so comprehensible?”, in [Zureck 1980], 61–70.
J.H. Holland,Adaptation in natural and artificial systems, MIT Press, 1992.
D. Lenat, “The role of heuristics in learning by discovery”, in [Michalski 1983]. 243–306.
G.O. Longo, “From Golem to Gödel and back”,Nuova civilità delle macchine 12, 1994, 28–38; reprinted inMacchine e automi, 1995, 75–108.
R. Michalski, inMachine learning: an artificial intelligence approach, vol. II, Morgan-Kauffman, 1986, 3–26.
D. Parisi, “Connessionismo, origine e sviluppo al centro dello studio dell'intelligenza”, inSistemi Intelligenti n. 3, 1990, 365–426.
K. Popper,Thought and experience and evolutionary epistemology, in Atti del convegnoChe cos'è il pensiero? Unità dell'essere, Accademia Nazionale dei Lincei, 1985, 349–353.
K. Popper,A world of propensities, Thoemmes Antiquarium Books, 1990.
P.A. Schilpp (ed.),The philosophy of Karl Popper, La Salle (Illinois), Open Court Publ., 1980.
M. Somalvico, “Emula, non simula”, in AAVV:Aspettando Robot, Edizioni Laterza, 1987, 172–181.
M. Somalvico, “Aspetti filosofici dell'intelligenza artificiale”, in Proceedings of AIIA-94, Parma 1994, 43–46.
L. Steels, “The artificial life roots of AI”, inA-life Journal 1, 1994, 89–125.
W. Zureck (ed.),Complexity, entropy and the physics of information, Add-Wesley, 1990.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Cristianini, N. Evolution and learning: An epistemological perspective. Axiomathes 6, 429–437 (1995). https://doi.org/10.1007/BF02228987
Issue Date:
DOI: https://doi.org/10.1007/BF02228987