Beginner's Guide to Deep Learning

We know how to predict the output from the given perceptron. Perceptron output can draw a boundary between the two classes. 


The boundary is not always accurate when model output is calculated the very first time.

# The best possible fit function 
We want the line to create the boundary that separates the two classes.

The following illustration helps you visualize this:

What did you observe in the illustration above? Are we moving the point closer to the line or the line closer to the misclassified point? 

<p>What did you observe in the illustration above? Are we moving the point closer to the line or the line closer to the misclassified point?</p>


> 📝 We are moving the line downwards if the star is misclassified and moving the line upwards if the square is misclassified.

# How to find the best possible fit?

Recall the perception equation for making a boundary line:
<center>

$ w_1x_1 + w_2x_2 + b = 0$

</center>
The prediction is  given by:

$\hat{y}$ = { 1 if  $w_1x_1 + w_2x_2 +... w_nx_n + b$ >= 0 and 0 otherwise}



The perceptron trick helps us to find the best possible line that separates the two classes.  Let's learn how?

Chapter 1

Perceptron Trick

The best possible fit function

Quiz

How to find the best possible fit?