The simplest definition of a neural network, more properly referred to as an 'artificial' neural network (ANN), is provided by the inventor of one of the first neurocomputers, Dr. Robert Hecht-Nielsen. He defines a neural network as:
"...a computing system made up of a number of simple, highly interconnected processing elements, which process information by their dynamic state response to external inputs.
In "Neural Network Primer: Part I" by Maureen Caudill, AI Expert, Feb. 1989
ANNs are processing devices (algorithms or actual hardware) that are loosely modeled after the neuronal structure of the mamalian cerebral cortex but on much smaller scales. A large ANN might have hundreds or thousands of processor units, whereas a mamalian brain has billions of neurons with a corresponding increase in magnitude of their overall interaction and emergent behavior. Although ANN researchers are generally not concerned with whether their networks accurately resemble biological systems, some have. For example, researchers have accurately simulated the function of the retina and modeled the eye rather well.
Although the mathematics involved with neural networking is not a trivial matter, a user can rather easily gain at least an operational understanding of their structure and function.
(Score: 1, Informative) by Anonymous Coward on Friday December 16 2016, @10:54PM
Neural Networks: A Systematic Approach by Rojas is my favorite book on neural networks; it is very readable. It starts with the very basics and moves on from there, and covers all the topics that you would expect from a first course on the subject. I particularly liked the construction that demonstrates that binary threshold networks can simulate any finite automaton.
(Score: 2) by driven on Saturday December 17 2016, @02:15AM
I have thousands of digital photographs I would like to categorize by who's in them and possibly by features (greenery, water, etc.).
I've used two off-the-shelf pieces of software for facial recognition and in both cases after many many hours of work the database gets corrupted.
So next time, I'd like to come up with my own solution, preferably using Python. Any recommendations on how to get started?