/Neural-Network-using-Numpy

Introduction to Neural Networks (Create a neural network using Numpy)

Primary LanguageJupyter NotebookMIT LicenseMIT

Neural-Network-using-Numpy

Introduction to Neural Networks (Create a neural network using Numpy)

In this assignment, you will build a complete neural network using Numpy. You will implement all the steps required to build a network - feedforward, loss computation, backpropagation, weight updates etc.

You will use the MNIST dataset to train your model to classify handwritten digits between 0-9.

The assignment is divided into the following sections:

  • Data preparation
  • Feedforward
  • Loss computation
  • Backpropagation
  • Parameter updates
  • Model training and predictions

For Ipython notebook: (Refer to Neural-Networks-using-Numpy.ipynb file)

For the dataset: (Refer to mnist.pkl.gz file)

Jupyter Notebook Viewer

If you are unable to view or load the jupyter IPython notebook via Github, please click on this link. Thank you!