Skip to content

Latest commit

 

History

History

03-perceptrons

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
6a-perceptron.py
6a-perceptron.py
 
 
README.md
README.md
 
 
statement.pdf
statement.pdf
 
 

README.md

Perceptron

  1. Adjust the code in order to get the plot to display correctly.

    Add line show() to the code.

  2. Look at the weights.

    a. What happens when there’s an incorrect prediction?

    The weights get changed.

    b. How big is the change in the weights?

    Depends on the learning rate.

    c. What’s the bias weight for?

    Adds a scalar value.

  3. Decrease the learning rate by factors of 10 (i.e. add zeros after the decimal point). What happens?

    The error varies.

  4. Increase the number of iterations. What happens?

    Not really sure (?)

  5. Adjust the training set to represent OR, XOR, and NAND. Which ones can the system generalise to? Why?

    With OR, all good. With XOR, it cannot be learnt. With NAND, all good.