Randomly Connected Sigma-Pi Neurons Can Form Associative Memories

A set of sigma-pi units randomly connected to two input vectors forms a disorganized type of hetero-associative memory related to convolution- and matrix-based associative memories. Associations are represented as patterns of activity rather than connection strengths. Decoding the associations requires another network of sigma-pi units, with connectivity dependent on the encoding network. Learning the connectivity of the decoding network involves setting n 3 parameters (where n is the size of the vectors), and can be accomplished in approximately 3e n log n presentations of random patterns. This type of network stores information in activation values rather than in weight values, which makes the information accessible to further processing. This is essential for higher-level processing. The functionality of such random networks makes it more plausible that these types of associative networks could have arisen during the course of evolution. 1 Introduction The ability to reason abou..