A Cortical Architecture for Parallel Anticipation of Sensorimotor Sequences - Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470

The basic idea o f our anticipatory approach t o perception is t o avoid the common separation o f perception and generation o f behavior and t o fuse both aspects in to a consistent neural process. Our approach is based on the prediction o f the consequences o f hypothetically executed actions. In this sense, perception o f space and shape is assumed t o be a generative process o f anticipating the course o f events resulting f rom different sequences o f actions. We present a biologically motivated computational model that is able to anticipate and evaluate,hypothetical sensorimotor sequences. Our Model for Anticipation based on Cortical Representations (MACOR) allows a completely parallel search at the neocortical level using assemblies o f rate coded neurons for grouping, separation, and selection o f sensorimotor sequences.