Neural Network from Scratch

This repository contains a Deep Neural Network implemented in scratch. The code is divided and kept as seperate .py files so that code is more readable. The architecture is explained completely in the .ipynb file in /MLP_from _scratch/ folder. The neural network is used for classification of results of Dota 2 games.

Acknowledgement

The Dataset used in this repository is from UCI Repositories.Visit https://archive.ics.uci.edu/ml/datasets/Dota2+Games+Results# to look at the detailed description of the data.

Dua, D. and Graff, C. (2019). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science.

Here is a BiBTeX citation as well:

@misc{Dua:2019 ,
  author = "Dua, Dheeru and Graff, Casey",
  year = "2017",
  title = "{UCI} Machine Learning Repository",
  url = "http://archive.ics.uci.edu/ml",
  institution = "University of California, Irvine, School of Information and Computer Sciences" 
}

Prerequisites

• Python 3.6
• Numpy 1.16.2
• Pandas 0.24.2
• IPython 7.5.0

To Clone Repository

• Type $ git clone https://github.com/THINK989/Neural-Network-from-Scratch.git in GIT Bash

To RUN it on your computer

Follow the steps given below:-

• Click on Download ZIP, and a .zip will be downloaded to your PC

• Then Open Jupyter Notebook, if you dont have jupyter notebook download Anaconda3

• If you already have jupyter notebook, open and create a new folder

• Then upload all the files from .zip file. Make sure you uplaid all the files in the same folder

Open Multi Layer Perceptron.ipynb and run each cell, play with the code. I recommend you to also visit all other .py files and try different option for different segments to understand the working even more precisely. The .ipynb file has all the details of architecture and an optional guide to play around with the code.