Neural Networks: Difference between revisions
Jump to navigation
Jump to search
| Line 9: | Line 9: | ||
[[Image:Neuron.png]] | [[Image:Neuron.png]] | ||
A common option is to use a [[Sigmoid_Function#Logistic_Function|logistic]] function as hypothesis, thus the unit is referred to as a logistic unit with a sigmoid ([[Sigmoid_Function#Logistic_Function|logistic]]) activation function. | |||
The θ vector represents the model's ''parameters'' (model's ''weights''). For a multi-layer neural network, the model parameters are collected in matrices named Θ, which will be describe below. | The θ vector represents the model's ''parameters'' (model's ''weights''). For a multi-layer neural network, the model parameters are collected in matrices named Θ, which will be describe below. | ||
Revision as of 02:35, 4 January 2018
Internal
Individual Neuron
Individual neurons are computational units that read input features, represented as an unidimensional vector x1 ... xn in the diagram below, and calculate the hypothesis function as output. Note that x0 is not part of the feature vector, but it represents a bias value for the unit.
A common option is to use a logistic function as hypothesis, thus the unit is referred to as a logistic unit with a sigmoid (logistic) activation function.
The θ vector represents the model's parameters (model's weights). For a multi-layer neural network, the model parameters are collected in matrices named Θ, which will be describe below.
The bias unit is optional, but when it is provided, it is always 1.
Multi-Layer Neural Network
When the output