Robohub.org
machine learning
Talking Machines: Common sense problems & learning about machine learning with Kevin Murphy
On episode three of Talking Machines we sit down with Kevin Murphy, who is currently a research scientist at Google. We talk with him about the work he’s doing there on the Knowledge Vault, his tex...
29 January 2015, by
Talking Machines
Talking Machines: Machine learning and magical thinking, with Ilya Sutskever
Robohub is excited to bring you our newest series - the Talking Machines podcast. Hosted by Katherine Gorman and Ryan Adams, Talking Machines is your window into the world of machine learning. Yo...
15 January 2015, by
Talking Machines
Teaching a robot to ‘cook’ by showing it YouTube videos of cooking shows
Most of us have at some point watched a video in order to learn how to do something. Our research shows that a robot can learn human actions by watching videos of humans performing those actions – i...
Introducing Talking Machines: Your window into the world of machine learning
Robohub is excited to bring you our newest series - the Talking Machines podcast. Hosted by Katherine Gorman and Ryan Adams, Talking Machines is your window into the world of machine learning. Yo...
01 January 2015, by
Talking Machines
“Chappie” movie to explore human reaction to AI, machine learning
A new action/sci-fi thriller by Neill Blomkamp (District 9, Elysium) is due in theatres March 6, 2015. Starring Sharlto Copley, Hugh Jackman, Dev Patel, and Sigourney Weaver, Chappie follows an exper...
04 November 2014, by
Hallie Siegel
Artificial General Intelligence that plays Atari video games: How did DeepMind do it?
Last December, an article named “Playing Atari with Deep Reinforcement Learning” was uploaded to arXiv by employees of a small AI company called DeepMind. Two months later [tweetquote]Google bough...
On internal models, consequence engines and Popperian creatures
So. We've been busy in the lab the last few months. Really exciting. Let me explain.
For a couple of years I've been thinking about robots with internal models. Not internal models in the classical...
08 September 2014, by
Alan Winfield
ShanghAI Lectures: Rüdiger Dillmann “Programming by Demonstration”
Guest talk in the ShanghAI Lectures, 2011-12-15
In this guest lecture, Rüdiger Dillmann from the Karlsruhe Institute of Technology, Germany, talks about paradigms for robot learning and the proper...
21 August 2014, by
Nathan Labhart
Signal processing technology to extract required information from image, sound, and biometric signals
At Keio University, the Mitsukura Laboratory, in the Department of System Design Engineering, researches how to extract required information from biometric, image, audio signal data. To achieve this, ...
26 May 2014, by
DigInfo TV
What should a robot do? Designing robots that know right from wrong
A large robot comes out of an office mailroom carrying a package marked “Urgent” to deliver to the boss upstairs. After navigating down the hall at maximum speed, it discovers someone is already w...
29 April 2014, by
AJung Moon and Footnote
What do teachers mean when they say ‘do it like me’?
This post is part of our ongoing efforts to make the latest papers in robotics accessible to a general audience.
Teaching robots to do tasks is useful, and teaching them in an easy and non time-i...
17 February 2014, by
Autonomous Robots Blog
Three new quadrotor videos demonstrate agile control and the power of machine learning
Quadrocopters assembling tensile structures in the ETH Flying Machine Arena. Photo credit: Professorship for Architecture and Digital Fabrication and the Institute for Dynamic Systems and Control, ETH...
18 November 2013, by
Hallie Siegel
Alex Zelinsky on “What are the five must-read publications for budding roboticists?”
The field moves quickly. So much of the material dates quickly. Joining a professional association such as IEEE or IFR and regular reading of publications - magazines and journals - is essential.
&...
15 December 2012, by
Alex Zelinksy
Why use robots, round 4
Machines can work continuously, 24/7. Doing so would require power enough to last through the night and either artificial lighting or night vision, and some operations are probably best left for dayli...
17 September 2007, by
John Payne
