• Martin Thoma
  • Home
  • Categories
  • Tags
  • Archives
  • Support me

ML Showcases

Contents

  • Image Input Data
    • Math Symbol Recognition
    • Drawings
    • Deep Dream
    • Style Transfer
    • Super-Resolution
  • Text Input Data
    • Translation
    • Sentiment Analysis
    • Text To Speech (TTS)
  • Other ML
    • Clustering
    • 2D Embeddings
    • Classifiers
  • Honorable Mentions

There are many awesome examples out there where you can get a very direct feeling for what Machine Learning is. I'll collect a couple of them here.

Image Input Data

Math Symbol Recognition

The write-math.com web service allows you to recognize mathematical symbols automatically. It is described in my bachelors thesis. The HWRT data is available, also in its rendered form as HASYv2 dataset.

write-math.com
write-math.com

Drawings

Quickdraw lets you recognize drawings. They built a database of 50 million drawings.

Quickdraw
Quickdraw

Using this kind of data, you can create an application which recognizes what was drawn and improves the drawing. autodraw.com does so:

autodraw.com: I wanted to draw a mouse (the animal)
autodraw.com: I wanted to draw a mouse (the animal)

Deep Dream

Deep Dream is a technique which needs a few more words to explain. You can read my paper Creativity in Machine Learning if you are interested in a very high level overview. If you just want to play with it, have a look at deepdreamgenerator.com.

Deep Dream of a Moon jelly
Deep Dream of a Moon jelly

Style Transfer

You have two images: A style image (e.g. by a painter) and a source image. You want the source image to be in the style of the style image:

Source image:

Original image of a highland cattle
Original image of a highland cattle

Style image:

Style image
Style image: Van Gogh - Starry Night

Output image:

Applied style transfer
Applied style transfer

https://deepart.io seems to be a web service for this kind of machine learning. I didn't try it, though.

Super-Resolution

You have a small image and want the same image, but with higher resultion? Search for "super resolution":

  • bigjpg.com
  • waifu2x.udp.jp

Text Input Data

Translation

DeepL.com is much better than https://translate.google.com, but also more restricted. As always, you can find some... interesting... translations:

DeepL Fail
DeepL Fail

Sentiment Analysis

Stanford NLP: Sentiment analysis
Stanford NLP: Sentiment analysis

Text To Speech (TTS)

Lyrebird.ai has the most impressive TTS system I have seen so far (although Googles Tacotron 2 audio samples are impressive as well).

Other ML

Clustering

Besides my small k-means clustering example, there is Tensorflow Projector

2D Embeddings

Mapping datapoints in 2D makes it easier to find what you are looking for. Have a look at fontmap:

Fontmap: Organizing fonts in 2D map
Fontmap: Organizing fonts in 2D map

Classifiers

Karpathy made a couple of interactive examples which show the decision boundaries of classifiers:

  • Random Forest
  • SVM
  • CNN
  • Neural Network
Tensorflow Playground: See how neural networks learn
Tensorflow Playground: See how neural networks learn

Honorable Mentions

  • howhot.io was a service which lets you upload an image with a face and rate how hot the person is. It is no longer available.
  • Microsoft Chatbot Tay went racist (source)
  • A visual introduction to machine learning
  • Martin Thoma, 2016: Creativity in Machine Learning
  • Alex Rogozhnikov, 2016: Gradient Boosting explained
  • Alex Rogozhnikov, 2016: Hamiltonian Monte Carlo explained
  • GridWorld: Dynamic Programming Demo
  • Wattenberg et al, 2016: How to Use t-SNE Effectively

Published

Dez 23, 2017
by Martin Thoma

Category

Machine Learning

Tags

  • Demo 1
  • Machine Learning 81

Contact

  • Martin Thoma - A blog about Code, the Web and Cyberculture
  • E-mail subscription
  • RSS-Feed
  • Privacy/Datenschutzerklärung
  • Impressum
  • Powered by Pelican. Theme: Elegant by Talha Mansoor