Multiclass pattern classification using neural networks

Multiclass neural learning involves finding appropriate neural network architecture, encoding schemes, learning algorithms, etc. In this paper, we discuss major approaches used in neural networks for classifying multiple classes. The discussion is focused d on these architectures using either a system of multiple neural networks or a single neural network. We will discuss various learning algorithms, One-Again-All, One-Against-One, and P-against-Q. We will also discuss training procedures associated with each approach, implementation and time complexity. These methods are evaluated though their performances on the NIST handwritten digit database.