Types of Transfer Functions
The transfer function of a neuron is chosen to have a number of properties which either enhance or simplify the network containing the neuron. Crucially, for instance, any multilayer perceptron using a linear transfer function has an equivalent single-layer network; a non-linear function is therefore necessary to gain the advantages of a multi-layer network.
Below, u refers in all cases to the weighted sum of all the inputs to the neuron, i.e. for n inputs,
where w is a vector of synaptic weights and x is a vector of inputs.
Read more about this topic: Artificial Neuron
Famous quotes containing the words types of, types, transfer and/or functions:
“... there are two types of happiness and I have chosen that of the murderers. For I am happy. There was a time when I thought I had reached the limit of distress. Beyond that limit, there is a sterile and magnificent happiness.”
—Albert Camus (1913–1960)
“He’s one of those know-it-all types that, if you flatter the wig off him, he chatter like a goony bird at mating time.”
—Michael Blankfort. Lewis Milestone. Johnson (Reginald Gardner)
“No sociologist ... should think himself too good, even in his old age, to make tens of thousands of quite trivial computations in his head and perhaps for months at a time. One cannot with impunity try to transfer this task entirely to mechanical assistants if one wishes to figure something, even though the final result is often small indeed.”
—Max Weber (1864–1920)
“The English masses are lovable: they are kind, decent, tolerant, practical and not stupid. The tragedy is that there are too many of them, and that they are aimless, having outgrown the servile functions for which they were encouraged to multiply. One day these huge crowds will have to seize power because there will be nothing else for them to do, and yet they neither demand power nor are ready to make use of it; they will learn only to be bored in a new way.”
—Cyril Connolly (1903–1974)