Self-organization of complex-like cells

Abstract

Proposes a new learning rule by which cells with shift-invariant receptive fields are self-organized. With this learning rule, cells similar to simple and complex cells in the primary visual cortex are generated in a network. To demonstrate the new learning rule, we simulate a three-layered network that consists of an input layer (the retina), a layer of S-cells (simple cells) and a layer of C-cells (complex cells). During the learning, straight lines of various orientations sweep across the input layer. Both S- and C-cells are created through competition. Although S-cells compete depending on their instantaneous outputs, C-cells compete depending on the traces (or temporal averages) of their outputs. For the self-organization of S-cells, only winner S-cells increase their input connections in a similar way to that for the neocognitron. In other words, LTP (long-term potentiation) is induced in the input connections of the winner cells. For the self-organization of C-cells, however, loser C-cells decrease their input connections (LTD=long-term depression), while winners increase their input connections (LTP). Both S- and C-cells are accompanied by inhibitory cells. Modification of inhibitory connections together with excitatory connections is important for the creation of C-cells as well as S-cells.