plutonurmux / imaginary-ai

Imaginary Artificial Intelligence —visualising my A.I. projects and research

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Imaginary A.I.

A portfolio-ish platform that helps visualize some of my interesting Artificial Intelligence projects and researches.

Deep Learning is a new area of Machine Learning research, which has been introduced with the objective of moving Machine Learning closer to one of its original goals: Artificial Intelligence.

After taking deep learning courses at MIT, Stanford Udacity and Coursera. I started working on projects to reinforce some fundamentals and also have fun with the new area of ML research.

Resources: You'll find interesting datasets on deeplearning.net and kaggle.com. Also find some useful blog posts on pinchofintelligence.com, Andrej Karpathy, Andrew Trask and Chris Olah's blog posts. To learn more about Neural Networks and it's various forms, your best bet is the neural network zoo

Projects

  • Image Classification
  • Generative Models
  • Image Search
  • A.I. Articles
  • Auto-encoding
  • Reinforcement Learning

Research

  • A language model
  • Project Glass
  • Exploration Exploitation Explanation

Dependencies

Setup

Clone this repo

git clone https://github.com/victor-iyiola/imaginary-ai.git

Or download the project here

Then change your working directory as show below

cd imaginary-ai

Install python dependencies

pip install --upgrade pip
pip install --upgrade -r requirements.txt

Install npm dependencies

cd static
npm install

After installing the dependencies. You can now start webpack (to compile all client files into a single javascript file. bundle.js)

For development

npm run watch

For Production

npm run build

Excellent. Now it's time to start the Python (flask) web server.

cd <imaginary-ai>
python run.py --debug=True

Contributions

This project is opened under MIT 2.0 license.

About

Imaginary Artificial Intelligence —visualising my A.I. projects and research

License:MIT License


Languages

Language:JavaScript 52.3%Language:SCSS 44.1%Language:Python 2.9%Language:HTML 0.8%