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

ML Review 3

Contents

  • New Developments
    • Human-strenght and Super-human strength programs
  • Live Demos and Websites
  • Publications
  • Software
  • Interesting Questions
  • Miscallenious
    • Trump QA idea
  • Meetings

This Review gives an overview of intersting stuff I stumbled over which are related to machine learning.

New Developments

  • Tensorflow 1.0 is released

Human-strenght and Super-human strength programs

Super-human strength programs are programs, which surpass even the best human (on the long run) in a specified task. Human-strength programs behave similar to an (untrained) human.

Although those are not new, seeing them as a list (source) was new to me. However, except for the games and lip reading, I doubt that we are there yet. Interesting, non the less:

  • Games
    • 1995, Checkers: Chinook
    • 1996, Chess: DeepBlue
    • 2016, Go: AlphaGo
  • Lip reading: 2016, Lip Reading Sentences in the Wild (YouTube)
  • Geolocation by photos, PlaNet - Photo Geolocation with Convolutional Neural Networks
  • Speech transcription: 2016, Achieving Human Parity in Conversational Speech Recognition
  • Translation: 2016, Zero-Shot Translation with Google’s Multilingual Neural Machine Translation System
  • Driving: 2016, Waymo

Live Demos and Websites

  • universe.openai.com: Related to the OpenAI gym.
  • Project Malmo: Train RL agents in Minecraft
  • VISIIR: VIsual Seek for Interactive Image Retrieval - classifying food
  • Image-to-Image

Publications

  • High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis and Code
  • The Game Imitation: Deep Supervised Convolutional Networks for Quick Video and YouTube playlist
  • Deep Nets Don't Learn Via Memorization

Software

Interesting Questions

  • Why is the accuracy of my CNN not reproducible?
  • How much does a GPU instance cost?

Miscallenious

Trump QA idea

I was just watching this clip and wodered how well a question answering system would work which is trained on Trump speaches. Very often, when reporters / journalists / moderators ask Trump a question, he answers with "I am the [most / best / least] [positive / negative statement]. [Inconsistent answer follows]". The answers themself would almost certainly be hilarous. Second, one could make an experiment and ask people if Trump actually answered a question like this.

Meetings

  • London, 4. December 2016: Data Visualization Challenge
  • Barcelona, 5. December 2016 - 10. December 2016: Neural Information Processing Systems (NIPS) (Link)
  • Mannheim, 7. April 2017: DataFest Germany
« Previous Review
Next Review »

Published

Feb 25, 2017
by Martin Thoma

Category

Machine Learning

Tags

  • 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