In this book, first, we introduce Huffman coding and present some examples for more clarification. We then present Huffman problems in form of some examples. Next, we explain Probability Density Function (PDF) for a stream. Our aim in this chapter is to fit a function on probability density curve representing an information stream using artificial Neural Network (NN). This methodology results in a specific function which represents a memorize able probability density curve. We then use the resulting function for information compression by Huffman algorithm. For this aim, first we introduce the basis of neural network with some examples and then we show popular transfer function using in NN. Also, we represent neural network structure which is applied in this chapter. We next propose two different algorithms for information encoding and decoding using time variable estimation of probability density function. In order to evaluate the proposed algorithm, the percentage of compression resulting from the proposed method has been compared with two popular methods named FDR code and Golomb at the end.