README.md

Machine Learning

• Introduction
• Workshop
• Reading list

Reading List

• Javascript
• Python
• Wekinator
• Machine Learning Disciplines
• Paid services
• Books and tutorials
• Community
• Demos and example projects

Javascript

Javascript allows us to publish our projects online, and provides easy ways to visualise our results using html and css.

Brain JS

BrainJS is a library that allows you to instantiate a Neural Network, train it and run a classification in just a few lines of code.

• Source code and examples for BrainJS
• Traversy BrainJS introduction
• Recognise letters
• Recognise a drawing and code
• Advanced Image feature detection using BrainJS

Tensorflow JS

The Javascript version of Google TensorFlow. TensorflowJS has lots of tutorials, and add-on libraries that make working with it even easier.

• Tensorflow for Javascript
• Hello World in Tensorflow.JS
• Basic tutorial for setting up Tensorflow Neural Network
• Tutorial course for Audio recognition
• Tutorial course for Webcam recognition

ML5

ML5 makes TensorFlowJS more accessible by supplying readymade examples with clear documentation for the most common Machine Learning projects, such as image classification, pose recogition, and text generation.

• Simplify working with TensorflowJS using the ML5 library

Pose Estimation using the Webcam with ML5 and TensorflowJS

Magenta JS

• Magenta is a google library that uses tensorflow to generate images, music and sketches.
• Tutorial on drawing snowflakes with a Neural Network and Magenta

Perceptron

A perceptron is a Neural Network that has only one cell. You can code it by hand in just a few lines of code. This will help you to understand how one Neural Network cell calculates weights.

• Coding a perceptron in Javascript, by Mathias P Johansson, and the result

Synaptic JS

Synaptic is another Neural Network Library for Javascript

• Synaptic JS Neural Networks
• Tutorial for Synaptic JS

Python

Python is used by data scientists and in many Machine Learning courses online. Python requires a bit more setup, especially when you want to visualise results graphically. Python can run on a Raspberry Pi!

• Udacity Intro to Machine Learning with Python
• Building a perceptron from scratch and source code
• Building camera detection on a raspberry pi

Science Kit Learn

Science Kit Learn provides Python libraries, readymade datasets and algorithms for testing, and a visualisation tool. Get started running python with this tutorial:

• SKLearn
• Introduction to machine learning with scikit-learn

Tensorflow

Tensorflow is Google's Machine Learning API for Python

• Google Tensorflow tutorials
• Getting Started with TensorFlow
• Introduction to Deep Learning and Tensorflow

Keras

Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow

• Why use Keras?
• Keras

Wekinator

Wekinator is a Graphical User Interface that can apply Machine Learning algorithms to Processing and Arduino sensor data.

• Wekinator
• Wekinator workshop by Kars Alfrink

Machine Learning Disciplines

• Image Recognition
• Natural Language Processing
• Speech Recognition
• Pose Estimation

Image recognition

• TrackingJS, an image recognition library for Javascript
• YOLO - you only look once Image recognition network, watch the cool intro movie!
• Vize.ai Recognize and automate your images
• Clarifai image and video recognition tool
• TensorFlow image recognition
• ImageNet - readymade training data for image recognition
• GoCV - Use the GO programming language for Computer Vision

Natural Language Processing

Understanding the meaning of written text

• What are word vectors?
• Understanding Word2Vec Video by Daniel Shiffman
• Natural Language Processing with Spacy.io

Speech Recognition

Converting spoken audio into text

• Mozilla Deep Speech - blog post and code
• Google TacoTron Self-learning Speech Synthesizer
• Pocket Sphynx Speech Recognition

Pose Estimation

• Pose Estimation with TensorflowJS

Paid services

• Microsoft Machine Learning APIs
• Apple Core ML framework
• Machine Learning on Amazon Web Services
• Amazon Machine Learning Free Course
• Amazon Deep Racer

Reading list

• The Mostly Complete Chart of Neural Networks
• Introduction to Deep Learning
• More algorithms for Machine Learning
• Neural Networks Wiki page
• Machine Learning for Humans
• Machine Learning for designers
• A visual introduction to Machine Learning
• Deep learning book
• Build more intelligent apps with machine learning(Apple)
• Researching the use of ML in creative applications
• Design in the era of the algorithm
• Human-Centered Machine Learning
• The UX of AI (Google Design)
• Linear algebra - the math behind ML algorithms
• Maths for Programmers
• Paul G Allen Course on Machine Learning algorithms
• Mastering Machine Learning with MatLab for Python
• Deep Learning Simplified - Youtube series
• Neural Networks and Deep Learning - book recommended by Tensorflow
• Deep Learning Gone Wrong - How ML expectations don't always match with results
• Read Arduino Sensor data from Node

Community

• AI Stackoverflow
• Kaggle - Machine Learning challenges

Demos and projects

• Classify an image in 5 lines of Javascript
• Teleport Vision - generates HTML from pen and paper sketches
• Build a perceptron in Processing
• Training a model in Unity using a neural network
• Neural Drum Machine and Voice-based beatbox created with MagentaJS
• Demo for creating a self-learning Flappy Bird in Javascript
• Algorithm notes
• Google AI experiments
• Building a cat detector on a Raspberry Pi
• Quick Draw! - Can a Neural Network detect a doodle?
• Pyro - Uber's AI programming language
• Runway - An app that adds ML to creative projects
• Pixling - Building a life simulation app with Neural Networks
• Building a self-driving Mario Kart using TensorFlow and documentation

The future

https://xkcd.com/1925/