Solving the Binding Problem with Separated Extraction of Information by Oscillatory Self-Organizing Maps

摘要

One solution to the binding problem is the hypothesis that property binding should be represented by phase-locking among neuronal oscillatory firing. We introduce this synchronous firing hypothesis into the self-organizing maps, or SOMs. Here we propose oscillatory self-organizing maps. Using the computer simulation, we show that our model composed of the oscillatory SOMs can separate and extract information of the shapes and the colors from two simultaneous inputs, solving the binding problem.