Title :
Information theory, complexity and neural networks
Author :
Abu-Mostafa, Yaser S.
Author_Institution :
California Inst. of Technol., Pasadena, CA, USA
Abstract :
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.<>
Keywords :
information theory; neural nets; complexity; computing power; feed-forward; feedback; information processing; information theory; learning by example; memory capacity; neural networks; Feedforward neural networks; Feedforward systems; Information processing; Information theory; Neural networks; Neurofeedback;
Journal_Title :
Communications Magazine, IEEE
