Vector representation of associative learning

I. P. Pavlov has shown that conditioned reflexes are selective both with respect to conditioned stimuli and to conditioned reflexes elicited by those conditioned stimuli. At the neuronal level, selective aspects of conditional stimuli are based on detectors selectively tuned to the respective stimuli. The selective aspects of conditioned reflexes are due to command neurons representing specific unconditioned reflexes. It can be assumed that conditioned reflexes result from association between selective detectors and specific command neurons. The detectors activated by a conditional stimulus constitute a combination of excitations--a detector excitation vector. The detector excitation vector acts on a command neuron via a set of plastic synapses--a synaptic weight vector. Plastic synapses are modified in the process of learning, making the command neuron selectively tuned to a specific conditioned stimulus. The selective tuning of a particular command neuron to a specific excitation vector referred to a conditioned stimulus is the basis of associative learning. The probabilities of conditioned reflexes elicited by conditional and differential stimuli implicitly contain information concerning excitation vectors that encode the respective stimuli. The contribution of the vector code to associative learning was explored combining differential color conditioning with intracellular recording from color-coding neurons. It is shown that colors in carps and monkeys are represented on a hypersphere in the four-dimensional space similar with human color space. The basis of the color space is constituted by red-green, blue-yellow, brightness, and darkness neurons.