EXPERIMENTS ON PATTERN-RECOGNITION BY CHEMICAL-KINETICS

Experiments on pattern recognition are: performed with a network of ei ght open, bistable, mass-coupled chemical reactors. A programming rule is used to determine the network connectivity in order to store sets of stationary patterns of reactors with low or high concentrations. Ex periments show that these stored patterns can be recalled from similar initial patterns. To our knowledge, this is the first chemical implem entation of a type of neural network computing device. The experiments on this small network agree with simulations and support the predicti ons of the performance-of large:networks.