Skip to content

Latest commit

 

History

History
27 lines (14 loc) · 848 Bytes

README.md

File metadata and controls

27 lines (14 loc) · 848 Bytes
Raw

A simple neural network

  • an implementation of a simple neural network
  • done in Python and Numpy, with no external machine learning framework used
  • understanding sentimental analysis

The purpose of this project was to understand the full architecture of a neural network and to visually break down what's going on while training to properly categorise sentiements.

DONE:

Setting up:
  • execute command ipython notebook from commandline in the same folder as NeuralNetwork-SentimentAnalysis.ipynb
  • when the broswer is open launch NeuralNetwork-SentimentAnalysis.ipynb
  • the dataset is too big and is not uploaded on Github, however, you can open a Github issue and i'll provide a link
Training:
  • run the cell segments in the vertical order

FURTHER IDEAS:

  • coming soon