Robohub.org
 

Talking Machines: Automatic Translation and t-SNE, with Hal Daume


by
08 July 2016



share this:
Reuters dataset (in 2D) landmark t-SNE using semantic hashing. Source: vdmaaten.github.io/tsne

Reuters dataset (in 2D) landmark t-SNE using semantic hashing. Source: vdmaaten.github.io/tsne

In episode thirteen of season two, we talk about t-Distributed Stochastic Neighbor Embedding (t-SNE), take a listener question about statistical physics, plus, speak with Hal Daume of the University of Maryland (who is great to follow on Twitter).


If you enjoyed reading this article, you may also enjoy:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.



tags:


Talking Machines is your window into the world of machine learning.
Talking Machines is your window into the world of machine learning.

            AUAI is supported by:



Subscribe to Robohub newsletter on substack



Related posts :

Watch the ICRA keynote and plenary talks

  16 Sep 2026
If you missed the conference you can catch up on IEEE TV.

Building and programming autonomous robots at the York Micromaze Hackathon

and   11 Sep 2026
From 25–27 August, UK RAS STEPS members came together for a three-day Micromaze Robot Hackathon.

Robotics roadmaps from around the world spotlight of the month: United States of America

US robotics researchers and industry are looking for a cohesive national robotics strategy.

Could robots help tackle loneliness? BBC’s Ann Droid raises questions about the future of care

  07 Sep 2026
While the series exaggerates what robots can currently do, some of the technology it depicts is already being tested.

Exploring the Moon will require rovers that can think for themselves – an upcoming NASA mission will test whether they can

  04 Sep 2026
NASA is planning to send three small rovers to the Moon to autonomously compute how to best explore a patch of ground.

Surviving the paper deluge: Notes from an ICRA panel on publishing, LLMs, and the future of peer review

Experts discuss peer-review challenges and possibilities for reshaping the process.

When expressive humanoid robots are awkward, people become wary – new brain study

  31 Aug 2026
People become more suspicious of a humanoid robot that makes errors, especially when the robot is an expressive conversation partner.



AUAI is supported by:







Subscribe to Robohub newsletter on substack




 















©2026.05 - Association for the Understanding of Artificial Intelligence