Abstract
We consider a simple stochastic unit realized by digital ANDs and ORs. The function of the unit is inspired by nerve cells found in brains of higher organisms. Information is carried by trains of pulses in time. Therefore, time is introduced into the model as an essential variable. Principles of stochastic computing are used to appropriately model weighted summation of inputs. The model unit allows to process analog information as is provided by observables of real environment. The statistical properties of the model are examined. The traditional saturation non-linearity of neurons emerges as a natural consequence of signal gating by “synapses”. Different schemes of synaptic modification are indicated.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Adrian ED (1932) The mechanism of nervous action. University of Pennsylvania Press, Philadelphia
Bullock, TH, Grinnell A, Orkland R (1977) Introduction to nervous systems. Freeman, San Francisco
Eccles J (1973) The understanding of the brain. McGraw-Hill, New York
Feller W (1976) An introduction to probability theory and its applications. Wiley, New York
Gaines BR (1969) Stochastic computation systems. In: Tou J (eds) Advances in information systems. Plenum Press, New York
Gaines BR (1987) Uncertainty as a foundation of computational power in neural networks. In: Caudill M, Butler C (eds) Proceedings of the 1st International IEEE Conference on Neural Networks, San Diego, Calif
Haken H (1988) Private communication
Hasenburg KH (1987) Private communication
Hebb DO (1949) The organization of behavior. Wiley, New York
Hemmerle WJ (1967) Statistical computations on a digital computer. Blaisdell, Waltham, Mass
Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci 79:2554–2558
Lewis ER (1983) The elements of single neurons: a review. IEEE Trans SMC- 13:702–710
McCulloch WS, Pitts W (1943) A logical calculus of ideas immanent in nervous activity. Bull Math Biophys 5:115–133
Massen R (1977) Stochastische Rechentechnik. Hanser, München
Omohundro SM (1987) Efficient algorithms with neural network behaviour. Complex Syst 1:273–347
Peretto P, Niez J (1986) Stochastic dynamics of neural networks. IEEE TA SMC-16:73–83
Ribeiro ST (1967) Random-pulse machines. IEEE TA EC-16:261–276
Stein RB (1967) The information capacity of nerve cells using a frequency code, Biophys J 7:797–826
Steinbuch K (1960) Die Lernmatrix. Kybernetik 1:36–45
Thompson DW (1917) On growth and form. Cambridge University Press, Cambridge
Von Neumann J (1956) Probabilistic logics and the synthesis of reliable organisms from unreliable elements. In: Shannon CE, McCarthy J (eds) Automata studies. Princeton University Press, Princeton
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Banzhaf, W. On a simple stochastic neuron — Like unit. Biol. Cybern. 60, 153–160 (1988). https://doi.org/10.1007/BF00202903
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00202903