Machine learning

My implementation of machine learning stuff

First of all should mention the research paper and accompanying code that I have done

Articles

Artificial Neural Networks (ANN)

• Yann LeCun - 1998 - Efficient BackPropogation
• Xavier Glorot - 2011 - Deep sparse rectifier neural networks
• Michael Nielsen - 2015 - Neural Networks and Deep learning

Convolutional Neural Networks (CNN)

• Yann LeCun - 1998 - Gradient-Based Learning Applied to Document Recognition
• Jianxin Wu - 2017 - Introduction to Convolutional Neural Networks
• Jay Kuo - 2016 - Understanding Convolutional Neural Networks with A Mathematical Model
• Kaiming He - 2015 - Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Dominik Scherer - 2010 - Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
• Adit Deshpande - 2016 - The 9 Deep Learning Papers You Need To Know About (Understanding CNNs Part 3)
• Rob DiPietro - 2016 - A Friendly Introduction to Cross-Entropy Loss
• Peter Roelants - 2016 - How to implement a neural network Intermezzo 2

Tools

• Vizualizatoin of CNN - Digit recognition

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

Prerequisites

See requirements.txt

conda 4.5.4
python 3.6.4
etc

Installing

Install anaconda 4 from the official site.

Then make aliasses for default versions of python and pip in the /.bashsrc:

alias python = python3
alias pip = pip3

Create and activate enviroment via anaconda and install all packages required in the requirements.txt

conda create yourenvname
source activate yourenvname

Authors

• Elzhan Zeinulla - Most of the work has been done as experiment or ML practice - zelzhan

• Karina Bekbayeva - Co-author of the resaerch paper and coding buddy - karinabk

License

This project is licensed under the MIT License - see the LICENSE.md file for details

Acknowledgments

• Inspired and guided with Adnan Yazici
• Glad to have good programming team "Depressed and Funny"