Information theory, complexity and neural networks

Yaser S. Abu‐Mostafa · IEEE Communications Magazine · 1989

Some of the main results in the mathematical evaluation of neural networks as information processing systems are discussed. The basic operation of feedback and feed-forward neural networks is described. Their memory capacity and computing power are considered. The concept of learning by example as it applies to neural networks is examined.>

Read the paper · More papers on PaperTik