| 词条 | Learning rule |
| 释义 |
An artificial neural network's learning rule or learning process is a method, mathematical logic or algorithm which improves the network's performance and/or training time. Usually, this rule is applied repeatedly over the network. It is done by updating the weights and bias levels of a network when a network is simulated in a specific data environment.[1] A learning rule may accept existing conditions (weights and biases) of the network and will compare the expected result and actual result of the network to give new and improved values for weights and bias.[2] Depending on the complexity of actual model being simulated, the learning rule of the network can be as simple as an XOR gate or mean squared error, or as complex as the result of a system of differential equations. The learning rule is one of the factors which decides how fast or how accurately the artificial network can be developed. Depending upon the process to develop the network there are three main models of machine learning:
See also
References1. ^{{cite book|title=Neural Networks: A comprehensive foundation|publisher=Prentice Hall|isbn=978-8178083001|pages=50-104|url=https://books.google.com.pk/books?ei=oY2hT8CYE-vT4QSjvemuCQ&id=bX4pAQAAMAAJ&dq=Neural+Networks%3A+A+comprehensive+foundation&q=learn+from+its+environment#search_anchor|author=Simon Haykin|edition=2nd|authorlink=Simon Haykin|accessdate=2 May 2012|chapter=Chapter 2: Learning Processes|date=16 July 1998}} 2. ^{{cite book|title=Artificial Intelligence: A Modern Approach|publisher=Prentice Hall|isbn=0-13-103805-2|pages=693-859|url=http://aima.cs.berkeley.edu/|author=S Russell, P Norvig|edition=3rd|authorlink=Peter Norvig|accessdate=20 Nov 2013|chapter=Chapter 18: Learning from Examples}} 2 : Artificial neural networks|Learning |
| 随便看 |
|
开放百科全书收录14589846条英语、德语、日语等多语种百科知识，基本涵盖了大多数领域的百科知识，是一部内容自由、开放的电子版国际百科全书。