new Layer(size, input_size, Neuron)
A single layer of neurons. Networks process input through multiple layers.
Parameters:
Name | Type | Description |
---|---|---|
size |
number | Number of neurons in the layer. |
input_size |
number | Length of input arrays. |
Neuron |
object | (optional) Class used to initialize neurons. Defaults to SigmoidNeuron. |
- Source:
Methods
neuron(i, neuron)
Getter / setter for the layer's neurons, individually.
Parameters:
Name | Type | Description |
---|---|---|
i |
number | Index of the neuron to get or set. |
neuron |
object | (optional) A single neuron, which replaces the i'th neuron. If undefined, returns the i'th neuron. |
- Source:
neurons(neurons)
Getter / setter for the layer's neurons.
Parameters:
Name | Type | Description |
---|---|---|
neurons |
array | (optional) A list of neurons to replace the layer's current neurons. If undefined, returns the list of current neurons. |
- Source:
process(input)
Given an array of input bits, returns the layer's output
when the input is applied to each neuron.
Parameters:
Name | Type | Description |
---|---|---|
input |
array | array of input bits |
- Source: