What Is a Feedforward Neural Network?

T.S. Adams

A feedforward neural network is a type of neural network where the unit connections do not travel in a loop, but rather in a single directed path. This differs from a recurrent neural network, where information can move both forwards and backward throughout the system. A feedforward neural network is perhaps the most common type of neural network, as it is one of the easiest to understand and configure. These types of neural networks are used in data mining and other areas of study where predictive behavior is required.

Feedforward neutral networks are used in data mining and other applications where predictive behavior is studied.
Feedforward neutral networks are used in data mining and other applications where predictive behavior is studied.

A neural network is an artificial intelligence network designed to loosely imitate the "thinking" processes of a human brain. By feeding strings of data into the network, the computer is given opportunities to "learn" the patterns flowing through it, enabling it to correctly identify answers and provide trend analysis. They are used in tasks where a certain degree of learning and pattern recognition is required, such as during data mining operations. Data mining is simply the analysis of trends from a collection of information, such as the analysis of consumer purchasing trends and stock market progressions.

Information traveling through a feedforward neural network goes into the input layer, travels through the hidden layer, and emerges from the outer layer of the network, providing the end user with an answer to their query. An input layer is simply the place where the user enters the raw data or parameters of the information. The meat of the transaction takes place in the hidden layer, where the computer falls back upon its "experience" of handling similar data to produce an estimated reply. The information is funneled through the output layer, where an answer is provided back to the end user.

A feedforward neural network typically becomes more efficient as the end user provide it with more and more experimental data. Much like calculating an average, a more accurate result will be reached from using a wide number of test events. For example, the probability of rolling a "1" on a six-sided die is 16.667 percent; but it will take hundreds or thousands of simulations before the calculated average is confirmed through the use of real-world data. Feedforward neural networks are the same; their responses will become more accurate with time and experience.

You might also Like

Discuss this Article

Post your comments
Forgot password?