Lightnews — Scholar-powered news

Reposted by Dileep George @dileeplearning

Blake Richards @tyrellturing.bsky.social · 15d

1/4) I’m excited to announce that I have joined the Paradigms of Intelligence team at Google (github.com/paradigms-of...)! Our team, led by @blaiseaguera.bsky.social, is bringing forward the next stage of AI by pushing on some of the assumptions that underpin current ML.

#MLSky #AI #neuroscience

Paradigms of Intelligence Team

Advance our understanding of how intelligence evolves to develop new technologies for the benefit of humanity and other sentient life - Paradigms of Intelligence Team

github.com

23 11 180

Reposted by Dileep George @dileeplearning

Aparna Nair @disabilitystor1.bsky.social · 21d

Jesus Christ.

It was my birthday recently and I sincerely considered not living anymore.
The worst part of all is that the parents who once supported me fully in being an artist sent me an AI generated picture of a caricature of themselves holding a birthday cake with my name spelled incorrectly.

49 1.4K 3.5K

Dileep George @dileeplearning @dileeplearning.bsky.social · 21d

Yes, it counts.

1

Reposted by Dileep George @dileeplearning

Abhilasha Joshi, PhD @rhythmicspikes.bsky.social · 21d

1/
🚨 New preprint! 🚨

Excited and proud (& a little nervous 😅) to share our latest work on the importance of #theta-timescale spiking during #locomotion in #learning. If you care about how organisms learn, buckle up. 🧵👇

📄 www.biorxiv.org/content/10.1...
💻 code + data 🔗 below 🤩

#neuroskyence

9 56 120

Dileep George @dileeplearning @dileeplearning.bsky.social · 21d

Thank you! Looks like I was able to fix it by adding one more rule to the domain forwarding setup at squarespace.

1 1

Dileep George @dileeplearning @dileeplearning.bsky.social · 21d

Hmmm….i need to vibe fix this….tomorrow!

1 1

Dileep George @dileeplearning @dileeplearning.bsky.social · 21d

#AGIComics now has a website! And it is 100% vibe coded!

Check out agicomics.net

AGI Comics — #23: Artificial General Productivity

A comic series.

agicomics.net

2 1 11

Reposted by Dileep George @dileeplearning

Sainsbury Wellcome Centre @sainsburywellcome.bsky.social · Aug 6

12 leading neuroscientists tackle a big question: Will we ever understand the brain?

Their reflections span philosophy, complexity, and the limits of scientific explanation.

www.sainsburywellcome.org/web/blog/wil...

Illustration by @gilcosta.bsky.social & @joanagcc.bsky.social

Illustration of the brain in blue and yellow

2 3 15

Dileep George @dileeplearning @dileeplearning.bsky.social · Jun 5

🎯

Dustin Moskovitz @moskov.goodventures.org · Jun 5

Note the date.

2 11

Dileep George @dileeplearning @dileeplearning.bsky.social · May 15

Ohh ok I realize that @tyrellturing.bsky.social mentioned evolution. Fine then. But then which neuroscientist believes this?

1 3

Dileep George @dileeplearning @dileeplearning.bsky.social · May 15

Hmm…I don’t think it’s impossible.

Evolution could create structures in the brain that are in correspondence with structure in the world.

Blake Richards @tyrellturing.bsky.social · May 14

Dear neuroscientists,

The brain cannot generate information about the world de novo, it's impossible.

All the brain can do is:

1. Selectively remove info that is irrelevant.
2. Re-emit info previously absorbed via evolution or memory.

Our brain never "creates" information. Never.

🧠📈 🧪

1 1 5

Dileep George @dileeplearning @dileeplearning.bsky.social · May 15

Here's the CSCG paper: www.nature.com/articles/s41...

And here' the CML paper:
www.nature.com/articles/s41...

Clone-structured graph representations enable flexible learning and vicarious evaluation of cognitive maps - Nature Communications

Higher-order sequence learning using a structured graph representation - clone-structured cognitive graphs (CSCG) – can explain how the hippocampus learns cognitive maps. CSCG provides novel explanati...

www.nature.com

2

Dileep George @dileeplearning @dileeplearning.bsky.social · May 15

Good conclusion :-).

1 1

Dileep George @dileeplearning @dileeplearning.bsky.social · May 15

somehow chatGPT understand my opinion about successor representations? 4/

1

Dileep George @dileeplearning @dileeplearning.bsky.social · May 15

I didn't mention partial observability specifically, so it is impressive that this was picked up. Looks like we did something right in our CSCG paper in making this explicit? 3/

1

Dileep George @dileeplearning @dileeplearning.bsky.social · May 15

It is quite impressive that chatGPT picked up these nuances, picks up a relevant quote from the paper and even emphasizes portions of the response. 2/

1

Dileep George @dileeplearning @dileeplearning.bsky.social · May 15

This paper turned up on a feed, I was intrigued by it and started reading...

..but then I was quite baffled because our CSCG work seem to have tackled many of these problems in a more general setting and it's not even mentioned!

So I asked ChatGPT... ...I'm impressed by the answer1. 1/🧵

1 1 11

Dileep George @dileeplearning @dileeplearning.bsky.social · Apr 29

Some of our work could explain this kind of latent graph learning and schema-like abstraction. 2/
arxiv.org/abs/2302.07350

Graph schemas as abstractions for transfer learning, inference, and planning

Transferring latent structure from one environment or problem to another is a mechanism by which humans and animals generalize with very little data. Inspired by cognitive and neurobiological insights...

arxiv.org

7

Dileep George @dileeplearning @dileeplearning.bsky.social · Apr 29

Wow, very cool to see this work from Alla Karpova's lab. She had shown me the results when I visited @hhmijanelia.bsky.social and I was blown away.

www.biorxiv.org/content/10.1...

1/

1 5 33

Dileep George @dileeplearning @dileeplearning.bsky.social · Apr 27

it takes a bit of getting immersed in the field to know this :-)

1 1

Dileep George @dileeplearning @dileeplearning.bsky.social · Apr 27

This comic would be an inside joke. Many neuroscience papers that study a brain region postulate that the current does a simple transformation of the input to make it easy for brain regions that are 'downstream' to solve the real problem effectively deferring the real problem. ...

1 1

Reposted by Dileep George @dileeplearning

PessoaBrain @pessoabrain.bsky.social · Apr 27

𝗛𝗼𝘄 𝘀𝗵𝗼𝘂𝗹𝗱 𝘄𝗲 𝗱𝗲𝗳𝗶𝗻𝗲 𝗮𝗻𝗱 𝗱𝗲𝘁𝗲𝗿𝗺𝗶𝗻𝗲 𝗮 𝗯𝗿𝗮𝗶𝗻 𝗿𝗲𝗴𝗶𝗼𝗻'𝘀 𝗶𝗺𝗽𝗼𝗿𝘁𝗮𝗻𝗰𝗲?
We introduce the idea of "importance" in terms of the extent to which a region's signals steer/contribute to brain dynamics as a function of brain state.
Work by @codejoydo.bsky.social
elifesciences.org/reviewed-pre...

Brain dynamics and spatiotemporal trajectories during threat processing

elifesciences.org

1 17 55

Dileep George @dileeplearning @dileeplearning.bsky.social · Apr 27

It's kinda obvious. #AGIComics has already figured out which brain region is the most important. 😇

3 5 25

Dileep George @dileeplearning @dileeplearning.bsky.social · Apr 26

And whether top-down't influence is multiplicative or not is very context-dependent. (this is also what is seen in neurobiology). www.science.org/doi/10.1126/...

1 5

Dileep George @dileeplearning @dileeplearning.bsky.social · Apr 26

www.science.org/doi/10.1126/...

1