Abstract: “The transmission of data across communication paths is an expensive process in respect time and bandwidth. Data compression is usually obtained by substituting a shorter symbol for an original symbol in the source data, which should contain the same information but with a smaller representation in length. The purpose of this paper is to show that neural networks may be promising tools for data compression without loss of information. We combine neural nets, standard statistical compression metho”

Keywords: Artificial Neural Network (ANN), statistical compression method, Back-propagation (BP), Hidden layer architecture, Weight matrix etc.