Data compression with multilayer perceptrons

The paper investigates the feasibility of using artificial neural networks as a tool for data compression. More precisely, the paper measures compression capabilities of one particular class of neural networks called multilayer perceptrons. An outline of a possible "neural" data compression method is given. Experiments are presented, where the outlined method has been simulated by using various data files and differently configured perceptrons. The best compression rates obtained in the experiments are listed and compared with similar results produced by some other network types, e.g. holographic neural networks.