Mcculloch Pitts Neuron Explanation – Simplest Way

[et_pb_section fb_built=”1″ _builder_version=”3.22″ fb_built=”1″ bb_built=”1″ _i=”0″ _address=”0″][et_pb_row make_equal=”on” module_class=” et_pb_row_fullwidth” _builder_version=”3.25″ width=”94%” width_tablet=”80%” width_last_edited=”on|desktop” max_width=”94%” max_width_tablet=”80%” max_width_last_edited=”on|desktop” module_alignment=”center” make_fullwidth=”on” _i=”0″ _address=”0.0″][et_pb_column type=”4_4″ _builder_version=”3.25″ custom_padding=”|||” _i=”0″ _address=”0.0.0″ custom_padding__hover=”|||”][et_pb_text _builder_version=”3.29.3″ hover_enabled=”0″ _i=”0″ _address=”0.0.0.0″]

Definition From Wikipedia

Wikipedia says An Artificial Neuron or The Mcculloch Pitts Neuron is a mathematical function conceived as a model of biological neurons, a neural network.

[/et_pb_text][et_pb_text _builder_version=”3.29.3″ hover_enabled=”0″ _i=”1″ _address=”0.0.0.1″]

And now we are going to see What is Mcculloch Pitts Neuron and we are going to learn the Mathematics behind this neuron in the simplest way.

So, Let’s Get Started.

[/et_pb_text][/et_pb_column][/et_pb_row][/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”3.22″ custom_padding=”54px|0px|32px|0px|false|false” fb_built=”1″ bb_built=”1″ _i=”1″ _address=”1″][et_pb_row make_equal=”on” _builder_version=”3.25″ module_alignment=”center” custom_padding=”40px|0px|20px|0px|false|false” _i=”0″ _address=”1.0″][et_pb_column type=”4_4″ _builder_version=”3.25″ custom_padding=”|||” _i=”0″ _address=”1.0.0″ custom_padding__hover=”|||”][et_pb_text _builder_version=”3.29.3″ text_font=”||||||||” ul_font=”||||||||” header_font=”||||||||” max_width_phone=”100%” max_width_last_edited=”on|phone” hover_enabled=”0″ max_width__hover_enabled=”on” max_width__hover=”100%” _i=”0″ _address=”1.0.0.0″]

What is Biological Neuron?

A biological neuron consists of Fours Parts Mainly,

  • Dendrite – Receives signals from other neurons.

  • Synapse – Point of connection to other neurons.

  • Soma – It’s the CPU, it processes the information.

  • Axon – Transmits the output of the neuron.

[/et_pb_text][/et_pb_column][/et_pb_row][et_pb_row _builder_version=”3.25″ _i=”1″ _address=”1.1″][et_pb_column type=”4_4″ _builder_version=”3.25″ custom_padding=”|||” _i=”0″ _address=”1.1.0″ custom_padding__hover=”|||”][et_pb_code _i=”0″ _address=”1.1.0.0″] style=”display:block; text-align:center;” data-ad-layout=”in-article” data-ad-format=”fluid” data-ad-client=”ca-pub-1750980986506231″ data-ad-slot=”3802595016″>[/et_pb_code][/et_pb_column][/et_pb_row][et_pb_row _builder_version=”3.25″ _i=”2″ _address=”1.2″][et_pb_column type=”4_4″ _builder_version=”3.25″ custom_padding=”|||” _i=”0″ _address=”1.2.0″ custom_padding__hover=”|||”][et_pb_text _builder_version=”3.27.4″ _i=”0″ _address=”1.2.0.0″]

Mccullouch Pitts Neuron

[/et_pb_text][/et_pb_column][/et_pb_row][et_pb_row column_structure=”3_5,2_5″ _builder_version=”3.25″ _i=”3″ _address=”1.3″][et_pb_column type=”3_5″ _builder_version=”3.25″ custom_padding=”|||” _i=”0″ _address=”1.3.0″ custom_padding__hover=”|||”][et_pb_image src=”https://tec4tric.com/wp-content/uploads/2018/10/mcculouch-pitts.png” align=”center” align_tablet=”center” align_last_edited=”on|desktop” _builder_version=”3.23″ _i=”0″ _address=”1.3.0.0″] 
[/et_pb_image][/et_pb_column][et_pb_column type=”2_5″ _builder_version=”3.25″ custom_padding=”|||” _i=”1″ _address=”1.3.1″ custom_padding__hover=”|||”][et_pb_text _builder_version=”3.29.3″ hover_enabled=”0″ _i=”0″ _address=”1.3.1.0″]

As you can see {X1, X2, X3, …, Xn∈ {0,1} are the Inputs and Y ∈ {0,1} is the Output. And f and g are the Functions.

f is the Activation Function and g is the Pre-Activation Function.

There are two types of inputs, One is Excitatory Input, which is dependent and another is Inhibitory Input, which is independent input.

Here {X1, X2, X3, …, Xn} ∈ {0,1} are the Excitatory Inputs.

Let’s understand the Math behind this neuron.

[/et_pb_text][/et_pb_column][/et_pb_row][et_pb_row _builder_version=”3.25″ custom_padding=”39px|0px|40px|0px|false|false” _i=”4″ _address=”1.4″][et_pb_column type=”4_4″ _builder_version=”3.25″ custom_padding=”|||” _i=”0″ _address=”1.4.0″ custom_padding__hover=”|||”][et_pb_code _i=”0″ _address=”1.4.0.0″] style=”display:block; text-align:center;” data-ad-layout=”in-article” data-ad-format=”fluid” data-ad-client=”ca-pub-1750980986506231″ data-ad-slot=”4841320570″>[/et_pb_code][et_pb_button button_url=”https://tec4tric.com/2018/09/top-10-machine-learning-projects.html” url_new_window=”on” button_text=”Top 10 Machine Learning Projects” button_alignment=”center” _builder_version=”3.16.1″ custom_button=”on” button_text_size=”25″ button_icon=”%%72%%” button_on_hover=”off” button_text_size_phone=”19″ button_text_size_last_edited=”on|phone” box_shadow_style=”preset1″ _i=”1″ _address=”1.4.0.1″] 
[/et_pb_button][/et_pb_column][/et_pb_row][/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”3.22″ custom_padding=”0|0px|54px|0px|false|false” fb_built=”1″ bb_built=”1″ _i=”2″ _address=”2″][et_pb_row _builder_version=”3.25″ _i=”0″ _address=”2.0″][et_pb_column type=”4_4″ _builder_version=”3.25″ custom_padding=”|||” _i=”0″ _address=”2.0.0″ custom_padding__hover=”|||”][et_pb_image src=”https://tec4tric.com/wp-content/uploads/2018/10/mccullouch-pitts1.png” align=”center” align_tablet=”center” align_last_edited=”on|desktop” _builder_version=”3.23″ max_width_last_edited=”on|phone” _i=”0″ _address=”2.0.0.0″] 
[/et_pb_image][et_pb_text _builder_version=”3.29.3″ text_font=”||||||||” header_font=”||||||||” hover_enabled=”0″ _i=”1″ _address=”2.0.0.1″]

The output will be 1 if g(x) is Greater than equal to ( ≥ ) the threshold parameter and the output will be 0 if g(x) is less than   ( < ) the threshold parameter.

I hope it is clear now.

[/et_pb_text][/et_pb_column][/et_pb_row][et_pb_row _builder_version=”3.25″ _i=”1″ _address=”2.1″][et_pb_column type=”4_4″ _builder_version=”3.25″ custom_padding=”|||” _i=”0″ _address=”2.1.0″ custom_padding__hover=”|||”][et_pb_code _i=”0″ _address=”2.1.0.0″] style=”display:block; text-align:center;” data-ad-layout=”in-article” data-ad-format=”fluid” data-ad-client=”ca-pub-1750980986506231″ data-ad-slot=”4841320570″>[/et_pb_code][/et_pb_column][/et_pb_row][et_pb_row _builder_version=”3.25″ _i=”2″ _address=”2.2″][et_pb_column type=”4_4″ _builder_version=”3.25″ custom_padding=”|||” _i=”0″ _address=”2.2.0″ custom_padding__hover=”|||”][et_pb_text _builder_version=”3.29.3″ hover_enabled=”0″ inline_fonts=”Caudex” _i=”0″ _address=”2.2.0.0″]

Notes: – 

A single Mcculloch Pitts neuron can be used to represent Boolean functions ( AND, OR, NOR, etc. ) which are linearly separable.

Linear Separability:

There exists a line ( plane ) such that all inputs which produce a 1 lie on one side of the line ( plane ) and all inputs which produce a 0 lie on another side of the line ( plane ).

[/et_pb_text][et_pb_text _builder_version=”3.27.4″ _i=”1″ _address=”2.2.0.1″]Source: NPTEL’s Deep Learning Course
[/et_pb_text][et_pb_post_nav in_same_term=”off” _builder_version=”3.15″ _i=”2″ _address=”2.2.0.2″] 
[/et_pb_post_nav][/et_pb_column][/et_pb_row][/et_pb_section]

Sayan De

Sayan De is pursuing his M.Tech in CSE. His interest area of work is Machine Learning, Deep Learning, Deep NLP, Computer Vision, Data Science, Linux, and a little bit of Website Development.

Leave a Reply

Your email address will not be published. Required fields are marked *