**Wikipedia** Says The **Perceptron** is a **Machine Learning algorithm** for **supervised learning** of binary classifiers. It is a type of linear classifier.

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

**So, Let’s Get Started.**

**First of All**, to Know about **Perceptron** you NEED to KNOW ” **What is Mcculloch Pitts Neuron?** “. My request to you to Read the blog post first, because, Mcculloch Pitts neuron and Perceptron are approximately Similar.

**Perceptron**

**Perceptron is a more general computational model than Mcculloch Pitts Neuron.**

**{X**are the

_{1, }X_{2, }X_{3, }…, X_{n}}**Inputs**and

**Y**is the

**Output**. And

**f**and

**g**are the

**Functions**. There are two types of inputs, One is

**Excitatory**Input, which is dependent and another is

**Inhibitory**Input, which is independent input. Here

**{X**are the Excitatory Inputs.

_{1, }X_{2, }X_{3, }…, X_{n}}**Here, (w**_{1}, w_{2}, w_{3}, …, w_{n} ) are the Weights.

_{1}, w

_{2}, w

_{3}, …, w

_{n}) are the Weights.

**The main difference between Mcculloch Pitts neuron and Perceptron is, an introduction of numerical weights (w**_{1}, w_{2}, w_{3}, … w_{n} ) for inputs and a mechanism for learning these weights.

_{1}, w

_{2}, w

_{3}, … w

_{n}) for inputs and a mechanism for learning these weights.

**This equation is same as the Mcculloch Pitts Neuron, Only here the Weights ( W ) are included. These Weights are going to learn and change which was not present in Mcculloch Pitts Neuron.**

**Look CAREFULLY, here we start at i = 0. Which means,**

**{ W _{0}X_{0} + W_{1}X_{1} + W_{2}X_{2} + …. + W_{n}X_{n } } ≥ 0**

**[ Now, putting W**

_{0}= – θ and X_{0}= 1 ], We will get,

**{ – θ + W**_{1}X_{1}+ W_{2}X_{2}+ …. + W_{n}X_{n }} ≥ 0**Which is Similar to the PREVIOUS equation where i starts at 1.**

*This W0 is called the Bias.*

*This W0 is called the Bias.*

**NOTE THAT:**

**From the equation, it should be clear that even a Perceptron separates the input space into two Halves.**

**All inputs which produce a 1 lie on one side and all inputs which produce a 0 lie one another side.**

**The difference is the weights can be learned and the inputs can be real-valued.**

Source: NPTEL’s Deep Learning Course