ML, robotics. (Gone to @benm@mathstodon.xyz)

Joined February 2007
17 Photos and videos
17 Jul 2023
Multi-agent robot learning: if that's your thing, you might be interested in our workshop at IROS 2023. djhanove.github.io/IROS23_MR… We have some great speakers, and if you have work to share, we are looking for submissions by August 20th!

3
431
Ben Moran retweeted
16 Apr 2023
These robots were told one thing: score. They taught themselves to play soccer – creating their own strategies and their own ways to walk, dribble and block. cbsn.ws/43GDktB
132
541
1,977
1,158,653
Ben Moran retweeted
Football players can tackle, get up, kick and chase a ball in one seamless motion. How could robots master these motor skills? ⚽ We trained AI agents to demonstrate these agile behaviours using end-to-end reinforcement learning. Find out more: dpmd.ai/41N3CsM
77
606
2,610
535,521
Ben Moran retweeted
30 Nov 2022
I have an unusual story to tell about how score-based generative models construct the data manifold. Will present this at @NeurIPS 2022 Score-Based Model workshop. A really enjoyable collaboration with @benm and many at @DeepMind paper: openreview.net/forum?id=eSZq…
1
3
51
Ben Moran retweeted
26 Oct 2018
You might think it’s just a video, but you’d be mistaken. We just released a series of “explorable videos” wherein @3blue1brown teaches you about quaternions and 3d rotation! Is this a new educational medium? eater.net/quaternions
17
128
535
21 Jul 2018
A bit close to the bone this time, @wyr_bot
27 Jun 2018
Would you rather get privacy or have the news all the time?
1
Ben Moran retweeted
25 Jun 2018
We would ask you to guess what this is, but it's just not going to happen. It's the paths of 800 unmanned bikes being pushed until falling over, from Matthew Cook. instagram.com/p/BkZh2ZQH1eB/… ^JH
6
33
100
27 Feb 2018
Air string of beauty is a joy forever. x.com/davidsd/status/9681942…

An example of interacting strings: i.imgur.com/AYFsZ7V.gifv
Ben Moran retweeted
18 Feb 2018
#NuitBlanche Posters: SysML 2018 Conference goo.gl/fb/5WPJnf #ml

1
20 Jul 2017
"Human empowerment" (Salge/Polani) buff.ly/2uJ4Klx (/cc @nikete @dbalduzzi just as we spoke about!)

2
6
Ben Moran retweeted
Using Inverse Reinforcement Learning to identify animal behavioral strategies biorxiv.org/content/early/20…
1
31
93
Ben Moran retweeted
Origami algorithm will help you fold paper like a master sciencemag.org/news/2017/06/…

1
2
Ben Moran retweeted
Impressive use of word2vec to help creating a version of the book of Genesis using only words starting with A: llamasandmystegosaurus.blogs…

2
72
124
Ben Moran retweeted
Professor Meredith Thring invented a stair climbing robot and here he is tooling up some stairs!
1
8
Ben Moran retweeted
1 Jun 2017
Cell, "Noninvasive deep brain stimulation via temporally interfering electric fields," authors.elsevier.com/a/1V8bl…

2
81
101
3 Apr 2017
"Paper fold strips can be constructed to solve equations up to degree 4". en.m.wikipedia.org/wiki/Math…
1
2
Ben Moran retweeted
little random walk though vector space made by averaging word embeddings of lines of poetry from project gutenberg
6
50
146
Ben Moran retweeted
Way more interesting than what the title would make you think: "Catching a Real Ball in Virtual Reality" youtube.com/watch?v=Qxu_y8AB…

1
12
21