The structure behind deep learning.
THE DEFINITION
Layers of simple units, each receiving inputs, combining them, and passing a result onward.
THE BIOLOGY ANALOGY
Loosely inspired by neurons. The resemblance is superficial.
HOW IT WORKS
Input enters the first layer, each layer transforms it, the final layer produces output.
Each connection carries a weight, adjusted during training.
WHAT TRAINING DOES
Adjusts millions or billions of weights so output matches the training examples.
WHY LAYERS HELP
Early layers detect simple features. Later layers combine them.
That progression is learned, not programmed.
WHAT IT REQUIRES
Very large amounts of data and substantial computation.
That is why these are built by well-resourced organisations and used by everyone else.
RELATED TERMS
Deep learning, parameter, training.
