Representing Spatial and Temporal Patterns in Neural Networks
Representing space and time is an important concern in knowledge engineering. Space might be represented in a neural network by:-
Using neurons that take spatial coordinates as input or output values. Fuzzy terms for indicating location, for instance "above," "near," and "in the middle" can also be used.
sing topological neural networks, that have distance defined between the neurons and can signify spatial patterns by their activations. Such a neural network is the SOM; it is a vector quantizer, which preserves the topology of the input patterns by representing one pattern as being one neuron in the topological output map.