A model of a neural network with recurrent inhibition has been studied. The model is intended as a possible description of the cerebral cortex, although this interpretation is not necessary. Using the corresponding neuroanatomical concepts, it can be described in the following way. The network consists of pyramidal cells and stellate cells. These are assumed to be of excitatory and inhibitory type, respectively. The input consists of excitatory signals and so-called unspecified signals. Both types of input are connected to the pyramidal cells. The output of the model is similarly formed by the output of these cells. However, the pyramidal cell output is also connected to the stellate cells. These are in their turn connected to the pyramidal cells, thus completing a closed circuit. All connections between cells are of random character. It is assumed that synapses can be facilitated as a result of simultaneous presynaptic and postsynaptic activity. This gives the model a capability of associative learning. The model's ability to retrieve information is investigated by studying the output in the absence of unspecified signals. It is shown that, under suitable conditions, the output pattern will become composed of just one major component even if the excitatory input pattern is a mixture of several patterns that were present during learning. This major component is a part of the specific output pattern that during learning became associated with the input pattern corresponding to the largest component of the pattern mixture. This behavior is obtained through a dynamic process in which the pattern separation properties of the feedback link play an important role. The model's operation can be viewed as pattern recognition and this aspect as well as some physiological and psychological interpretations are discussed.