Skip to content

Latest commit

 

History

History
48 lines (31 loc) · 1.4 KB

File metadata and controls

48 lines (31 loc) · 1.4 KB

Backpropagation


If you are building your own neural network, you will definitely need to understand how to train it. Backpropagation is a commonly used technique for training neural network.

Prerequisites


Python3 Installation :

-> Python3 : https://www.python.org/downloads/

Jupyter-Notebook Installation :

-> If you want to run ipython notebook(.ipynb file), So for run this file you need jupyter-notebook, if not already installed in your machine check below link for installation : https://jupyter.readthedocs.io/en/latest/install.html

Initialization


  • Sigmoid function (1/(1 + exp(-x)))
  • Unit vector ( X )
  • Target value that we want to predict using backpropagation
  • Learning rate ( α )
  • Weight for Input ⇒ Hidden layer.

Feed-Forward


We will use given weights and inputs to predict the output. Inputs are multiplied by weights and then the results are passed forward to the next layer.

Screenshot

Backpropagation


Screenshot

2. For run the Jupyter-Notebook :


-> Type jupyter-notebook in your terminal.

-> Go to Jupyter Navigation Bar -> Select 'Cell' -> Select 'Run All'

All set !!!