Tweet

Sebastian Risi

Follow @risi1979

14 Dec, 5 tweets, 5 min read

Finally done with my first blog post "The Future of Artificial Intelligence is Self-Organizing and Self-Assembling"!

sebastianrisi.com/self_assemblin…

Covering work from our group and others on the combination of ideas from deep learning and self-organizing systems.

@enasmel

Based on work by @enasmel, @JoachimWinther, @zzznah, @Smearle_RH, @togelius, @LouisKirschAI, @SchmidhuberAI, @SudhakaranShyam, @hardmaru, @pathak2206, @yujin_tang, @stenichele, @BertChakovsky, and many others. Looking forward to your comments!

https://twitter.com/GoodAIdev/status/1468810963658944516

Ideas from collective systems are slowly capturing the interest of the larger machine learning community. Very much looking forward to this workshop:

https://twitter.com/GoodAIdev/status/1468810963658944516

@hardmaru

Also check out this excellent and related review article on "Collective Intelligence for Deep Learning: A Survey of Recent Developments" by @hardmaru & @yujin_tang.

arxiv.org/abs/2111.14377

@pyoudeyer

And work by @pyoudeyer, @SidneyPontesF, @A_Variengien.

• • •

Missing some Tweet in this thread? You can try to force a refresh

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @risi1979

Sebastian Risi

@risi1979

17 Mar

Excited to share our work on Morphogenesis in Minecraft! We show that neural cellular automata can learn to grow not only complex 3D artifacts with over 3,000 blocks but also functional Minecraft machines that can regenerate when cut in half 🐛🔪=🐛🐛

PDF:arxiv.org/abs/2103.08737

@SudhakaranShyam

Very proud of the team @SudhakaranShyam , @DjordjeGrbic2, @Sylvia_Sparkle, @AdamKat0na, @enasmel, @claire__aoi. Hopefully of interest to @kenneth0stanley, @Smearle_RH, @pyoudeyer, @BertChakovsky. Maybe Minecraft+NCAs will be the building block of @gregeganSF's permutation city?😄

@zzznah

Inspired by @zzznah, @RandazzoEttore, @eyvindn, @drmichaellevin, @blaiseaguera, @ch402 work, we train a network in a supervised way to grow target structures, extending their approach from 2D to 3D.

https://twitter.com/zzznah/status/1227281246633349125

Read 8 tweets

Sebastian Risi

@risi1979

7 Jul 20

@enasmel

@enasmel and myself are excited to announce our paper "Meta-Learning through Hebbian Plasticity in Random Networks" arxiv.org/abs/2007.02686

Instead of optimizing the neural network's weights directly, we only search for synapse-specific Hebbian learning rules. Thread 👇

Starting from completely random weights, the discovered Hebbian rules enable an agent to navigate a dynamical 2D-pixel environment; likewise they allow a simulated 3D quadrupedal robot to learn how to walk in around 40 timesteps in the absence of any explicit reward.