Neuron

Neurons

Useful Links

• Neural Network Basics
• The Role of Bias in Neural Networks

Usage

Properties

Key	Type	Default	Description
connections	[Connection]	[]	All neuron connections
bias	Number	Math.random()	Check Out: The Role of Bias in Neural Networks
learning_rate	Number	0.3	Check Out: What is a "Learning Rate" in a Neural Network? Learning Rates and Deep Learning Performance
activation	"relu"|"sigmoid"|"tanh"|"step"|"linear"|"leaky-relu"|"softmax"|Function	"sigmoid"	Check Out: Fundamentals of Deep Learning: Activation Functions Understanding Activation Functions in Neural Networks Activation Functions: Neural Networks
	</td>

Key	Description
connections	All neuron connections
bias	Check out: The Role of Bias in Neural Networks
learning_rate	Check out: Overview: What is a "Learning Rate" in a Neural Network

Instance Functions

Key	Description
Neuron.prototype.is.input()	Tests whether neuron has no input connections
Neuron.prototype.is.output()	Tests whether neuron has no output connections
Neuron.prototype.connect()	Connects to another neuron, layer, or group
Neuron.prototype.inputs()	List of incoming connections
Neuron.prototype.outputs()	List of outgoing connections
Neuron.prototype.activate()	Activation function of neuron
Neuron.prototype.forward()	Forward propagates results of Neuron.prototype.activate()
Neuron.prototype.learn()	Updating function of neuron
Neuron.prototype.backward()	Backward propagates results of Neuron.prototype.activate()

Class Constants

Key	Description
Neuron.activation	An object of typical activation/squash functions
Neuron.activation.SIGMOID	sigmoid Squash Function
Neuron.activation.ReLU	ReLU Squash Function
Neuron.activation.TANH	tanh Squash Function
Neuron.activation.IDENTITY	identity Squash Function
Neuron.activation.PERCEPTRON	perceptron Squash Function
Neuron.update	An object of typical activation/squash function derivatives
Neuron.activation.SIGMOID	sigmoid Squash Function Partial Derivative
Neuron.activation.ReLU	ReLU Squash Function Partial Derivative
Neuron.activation.TANH	tanh Squash Function Partial Derivative
Neuron.activation.IDENTITY	identity Squash Function Partial Derivative
Neuron.activation.PERCEPTRON	perceptron Squash Function Partial Derivative

new Neuron()

• new Neuron(): Creates a new neuron.
• new Neuron({ inputs: [n0, n1], outputs: [n2] }): Creates a new neuron with n0 and n1 as incoming connections, and n2 as an outgoing connection.
• new Neuron(n0): Creates a new neuron with the same connections as n0

.is.input([callback])

• neuron.is.input(): Returns true if neuron has no incoming connections

.is.output([callback])

• neuron.is.output(): Returns true if neuron has no outgoing connections

.connect(object[, callback])

• neuron.connect(other_neuron): Connects neuron to other_neuron
• neuron.connect(layer): Connects neuron to every neuron in layer
• neuron.connect(group): Connects neuron to every neuron in group

.inputs([callback])

• .inputs(): Returns a list of incoming connections to neuron

.outputs([callback])

• .outputs(): Returns a list of outgoing connections from neuron

.activate(inputs[,callback])

• .activate([0, 1, 0, 1]): Activates neuron with the given inputs; inputs.length must equal connections.length

forward([callback])

• .forward(): Propagates the last result of .activate() to all outgoing connections

.learn(feedback[,callback])

• .learn([1, 0, 1, 0]): Calculates incoming connection errors

.backward([callback])

• .backward(): Propagates the last results of .learn() to all incoming connections