Order and rank of neural networks

Any boolean function can be expressed as a higher order threshold function. This means that logic networks may be treated as higher order neural networks. The author defines two complexity indices of logic networks when they are viewed as higher order neural networks. One is an order index: this reflects degree of parallelism employed at each element in processing information. The other is a rank index which is simply the rank of the weight matrix: this has to do with a new interpretation of neural networks from the viewpoint of neuroregulators.