Artificial neuron: Difference between revisions

From Citizendium
Jump to navigation Jump to search
imported>Felipe Ortega Gutiérrez
No edit summary
imported>Ro Thorpe
mNo edit summary
 
(18 intermediate revisions by 2 users not shown)
Line 1: Line 1:
'''Artificial neurons''' are processing units based on the biological neural model. The first artificial neuron model was created by McCullough and Pitts, and then newer and more complex models have appeared. Since the connectivity in the biological neurons is higher, artificial neurons must be considered as only an approximation to the biological model.
{{subpages}}


Artifical neurons can be organized and connected in order to create [[Artificial Neural Network|artificial neural networks]], which process the data carried through the neural connections in different layers. Learning algorithms can also be applied to artificial neural networks in order to modify their behavior.
'''Artificial neurons''' are processing units based on a neural model, often inspired on the biological neurons. The first artificial neuron model was created by McCullough and Pitts, since when newer and more realistic models have appeared.


[[Image:artificialneuron.png|thumb|300px|McCullough-Pitts neuron with 4 inputs.]]
Artificial neurons can be associated in order to create [[Artificial Neural Network|artificial neural networks]], which process the data carried through the neural connections.
 
[[Image:artificialneuron.png|thumb|450px|Artificial neuron with 4 inputs.]]


==Behavior==
==Behavior==
A neuron may have multiple inputs, each input has an assigned value called ''weight'', which represents the strength of the connection between the source and destination neuron. The input signal value is multiplied by the ''weight'' <math>w \in \left[0 \dots 1\right]</math>.
Neural processing involves the following operations:
 
The sum of all input values multiplied by their respective weights is called ''activation'', or ''weighted-sum''.
 
<math>a = \sum_{i=0}^n w_i x_i</math>
 
After the activation is produced, a function modifies it, producing an output. That function is often called ''transfer function'' and its purpose is to filter the activation.
 
<math>y = \varphi \left( \sum_{i=0}^n w_i x_i \right)</math>
 
==Transfer Functions==
'''Transfer functions''' is the name given for the functions which apply the threshold to the activation value. This functions can be discrete or continuous, and they also can be defined as step functions.


==Impulse pass==
a) Synaptic operation. Processes incoming data, considering the strength of each connection (often represented as a value called ''weight'').
Depending on the network model, neurons can pass their impulses to their terminals, or backwards. The "backward pass" can be observed in learning algorithms like "Backpropagation".


==Analogy to Biological Neurons==
b) Somatic operation. Provides operations such as thresholding, aggregation, non-linear activation and dynamic processing to the synaptic inputs. Most of these operations are used to implement a threshold effect.
In biological neurons there is a similar behavior. Inputs are electrical pulses transmitted to the [[synapses]] (terminals in the dendrites). Electrical pulses produce a release of [[neurotransmitter|neurotransmitters]] which may alter the dendritic membrane potential (''Post Synaptic Potential''). The Post Synaptic Potential travels over the axon, reaching another neuron, which will sum all the Post Synaptic Potentials received, and fire an output if the total sum of the Post Synaptic Potentials in the axon hillock received exceeds a threshold.


[[Category:CZ Live]]
==Analogy to biological neurons==
[[Category:Computers Workgroup]]
In biological neurons there is a similar behavior. Inputs are electrical pulses transmitted to the [[synapses]] (terminals in the dendrites). Electrical pulses produce a release of [[neurotransmitter|neurotransmitters]] which may alter the dendritic membrane potential (''post-synaptic potential''). The post-synaptic potential travels over the axon, reaching another neuron, which will sum all the post-synaptic potentials received, and fire an output if the total sum of the post-synaptic potentials in the axon hillock received exceeds a threshold.

Latest revision as of 20:01, 3 August 2009

This article is a stub and thus not approved.
 Main Article
 Discussion
Related Articles  [?]
Bibliography  [?]
External Links  [?]
Citable Version  [?]
 
https://en.citizendium.org/wiki/index.php?title=Artificial_neuron&printable=yes
This editable Main Article is under development and subject to a disclaimer.

Artificial neurons are processing units based on a neural model, often inspired on the biological neurons. The first artificial neuron model was created by McCullough and Pitts, since when newer and more realistic models have appeared.

Artificial neurons can be associated in order to create artificial neural networks, which process the data carried through the neural connections.

Artificial neuron with 4 inputs.

Behavior

Neural processing involves the following operations:

a) Synaptic operation. Processes incoming data, considering the strength of each connection (often represented as a value called weight).

b) Somatic operation. Provides operations such as thresholding, aggregation, non-linear activation and dynamic processing to the synaptic inputs. Most of these operations are used to implement a threshold effect.

Analogy to biological neurons

In biological neurons there is a similar behavior. Inputs are electrical pulses transmitted to the synapses (terminals in the dendrites). Electrical pulses produce a release of neurotransmitters which may alter the dendritic membrane potential (post-synaptic potential). The post-synaptic potential travels over the axon, reaching another neuron, which will sum all the post-synaptic potentials received, and fire an output if the total sum of the post-synaptic potentials in the axon hillock received exceeds a threshold.

Retrieved from "https://citizendium.org/wiki/index.php?title=Artificial_neuron&oldid=24316"