What is a Neural Network

Another Example: Real Estate Appraisal Consider a real estate appraiser whose job is to predict the sale price of residential houses. As with the Bank Loans example, the input pattern consists of a group of numbers. This problem is similar to the Bank Loans example, because it has many non-linearities, and is subject to millions of possible inputs patterns. The difference here is that the output prediction will consist of a calculated value -- the selling price of the house. It is possible to train the neural network to simulate the opinion of an expert appraiser, or to predict the actual selling price.