Abstract
The progress in artificial intelligence enables us to conceive adaptive systems whose characteristics are nearer and nearer to those of living beings. These characteristics though depend on ingenious choices by the designer of these systems: Initial conditions, parameters, optimisation functions, gradient and measure of fitness within the environment. Nevertheless, in living systems which are non-finalist, there are no programmers or designers to conceive of such ingenious choices.
Our paper “Self-Programming Machines (I)” presents a non-finalist model since initial states and functions are randomly chosen at the beginning and once and for all. In spite of the fact that they are non-finalist, these machines always stabilise at fixed points when they are connected to an external process.
This paper studies the dynamics of a mono-layered network of self-programming machines driving a real device, “the Ashby homeostat”, and shows the striking properties of such networks. This system stabilises only at fixed points even if it is subjected to small perturbations or intentional breakdowns such as a reversal of power supply or disconnection of one or several motors.
Real and simulated experiences are compared and theoretical results are demonstrated.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
REFERENCES
Ashby, W.R. (1952). Design for a Brain. Chapman & Hall, London.
Ashby, W.R. (1961). Principles of self-organising systems. Proceedings of the Western Joint Computer Conference. pp. 255–278.
Bartlett, S.J. and V. Suber (1987). Self-Reference. Martinus Nijhoff Publishers, Dordrecht.
Fogel, L.J., P.J. Angeline and D.B. Fogel (1995). An evolutionary programming approach to self-adaptation on finite states machines. In: McDonnell, J.R., R.G. Reynolds and.B. Fogel(Eds). Evolutionary Programming IV. MIT Press, Cambridge MA. pp. 355–365.
Hopfield, J.J. (1982). Neural network and physical system with emergent collective computational abilities. Proceedings of the National Academy of Sciences 79: 2554–2558.
Marina, A. (1915). EsDie Relationen des Palaeencephalons sind nicht fix. Neurologisches Centralblatt 34: 338.
Maturana, H.R. and F.J. Varela (1980). Autopoiesis and Cognition. D. Reidel, Dordrecht.
Moulin, J-P. (1992). Modifiable automata, Self-modifying automata. Acta Biotheoretica 40: 195–204.
Moulin, J-P. (1999). Very simple models, the self-modifying automata and chain of selfmodifying automata, can explain self-referential properties of living beings. Acta Biotheoretica 47: 353–365.
Moulin, J-P. (2000). Self Programming Machines (I). http://self-programming-machines.org/
Press, W.H., B.P. Flannery, S.A. Teukolsky and W.T. Vetterling (1986). Numerical Recipes. Cambridge University Press, New York.
Rumelhart, D. D., Hinton, G. E. and William, R. J. (1986). Learning representations by backpropagating errors. Nature 323: 533–536.
Sperry, R. W. (1947). Effects of crossing nerves to antagonistic limbs muscles in the monkey. Archives of Neurology and Psychiatry 58: 542.
Shutt, J. and R. Rubinstein (1995). Self-modifying finite automaton: An introduction. Information Processing Letters 56: 185–190.
Wang, Y., K. Inoue, A. Ito and T. Okazaki (1999). A note on self-modifying finite automata. Information Processing Letters 72: 19–24.
Zeleny, M. (1981). Autopoiesis: A theory of living organisation. Elsevier, New York.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Moulin, JP. Self-Programming Machines (II): Network of Self-Programming Machines Driving an Ashby Homeostat. Acta Biotheor 51, 265–276 (2003). https://doi.org/10.1023/B:ACBI.0000003983.86071.a0
Issue Date:
DOI: https://doi.org/10.1023/B:ACBI.0000003983.86071.a0