Mini tensor flow

This project is a simplified version of TensorFlow, which uses a neural network to predict the price of homes in the Boston area.

Motivation

Understand differentiable graphs and backpropagation, implementing a neural network from scratch.

Built With

• Python 3 - Language
• Anaconda - Python Data Science Platform

Dataset

The dataset was obtained from the scikit-learn library.

Getting Started

Prerequisites

1. Download and install Anaconda
2. Update Anaconda

$ conda upgrade conda 
$ conda upgrade --all 

Install

1. Clone and enter into the project's root directory by command line

$ git clone https://github.com/machine-learning-experiments/mini-tensor-flow.git

2. Create and activate enviroment

$ conda env create -f enviroment.yaml 
$ conda activate mini-tensor-flow

or

conda create --name mini-tensor-flow python=3
source activate mini-tensor-flow
conda install numpy scikit-learn

3. Execute neural network for see the loss value tend to zero

$ python neural_network.py 

Author

Lorival Smolski Chapuis

This project was developed during the deep-learning nanodegree from Udacity