Feed-forward neural networks (FFNN)
The idea behind artificial neural networks was to build mathematical and computational models of the natural neural network in the brain. After all, the brain is a very powerful information processing engine that surpasses computers in domains such as learning, inductive reasoning, prediction and vision, and speech recognition.
The Biological background
In biology, a neural network is composed of groups of neurons interconnected though synapses [9:1], as shown in the following image:
Neuroscientists have been especially interested in understanding how the billions of neurons in the brain can interact to provide human beings with parallel processing capabilities. The 60s saw a new field of study emerging, known as connectionism. Connectionism marries cognitive psychology, artificial intelligence, and neuroscience. The goal was to create a model for mental phenomena. Although there are many forms of connectionism, the neural network models have become the...
