Trending
Niels Leadholm's Avatar

Niels Leadholm

@cortical-canonical

Research lead @thousandbrains.org‬ (AI/ML) Prev. RS @numentaofficial.bsky.social‬ + PhD in neuro-inspired AI at @ox.ac.uk Working on sensorimotor machine intelligence

70
Followers
158
Following
16
Posts
20.11.2024
Joined
Posts Following

Latest posts by Niels Leadholm @cortical-canonical

Great idea, will reach out to him and see if he'd be interested.

06.03.2026 09:01 👍 1 🔁 0 💬 0 📌 0

Looks interesting! Do you happen to know if there's going to be a public recording?

04.03.2026 09:41 👍 1 🔁 0 💬 1 📌 0
Post image

Reminder! Dec 17 at 9 AM PST: Jeff Hawkins, @vivianeclay.bsky.social, @cortical-canonical.bsky.social, and the Thousand Brains Project team will give a simple, easy-to-follow intro to the Thousand Brains Project and the machine intelligence we are building.
👉 Join us: www.meetup.com/thousand-bra...

15.12.2025 18:24 👍 4 🔁 2 💬 0 📌 0

I guess it’s now well established that locomotion boosts the signal-to-noise ratio of visual cortical responses in mice. Is there any evidence that locomotion also enhances visual recognition performance at the behavioral level?

26.11.2025 15:25 👍 4 🔁 1 💬 0 📌 1
Post image

Join us Dec 17 at 9 AM PST for a meetup with Jeff Hawkins, @vivianeclay.bsky.social, and the Thousand Brains Project team.

New to Monty? This is the perfect place to jump in. If you already know Monty, we’ll tell you something new.

www.meetup.com/thousand-bra...

26.11.2025 21:03 👍 4 🔁 2 💬 0 📌 1
What Neuroscience Insight was Non-Negotiable in the Design of Monty? #sensorimotorai #ai
What Neuroscience Insight was Non-Negotiable in the Design of Monty? #sensorimotorai #ai YouTube video by Thousand Brains Project

🚨 @cortical-canonical.bsky.social responds: What Neuroscience Insight was Non-Negotiable in the Design of Monty?

youtube.com/shorts/2DwYk...

Read the paper: arxiv.org/abs/2507.04494
Read the plain language explainer: thousandbrains.org/thousand-bra...

#AI #Neuroscience #SensorimotorAI

14.08.2025 18:16 👍 2 🔁 3 💬 0 📌 0
How Does Monty Deal with Noise and Novel Rotations? #ai #sensorimotorai
How Does Monty Deal with Noise and Novel Rotations? #ai #sensorimotorai YouTube video by Thousand Brains Project

🚨 @cortical-canonical.bsky.social responds: How Does Monty Deal with Noise and Novel Rotations?

youtube.com/shorts/Ci8ua...

Read the paper: arxiv.org/abs/2507.04494
Read the plain language explainer: thousandbrains.org/thousand-bra...

#AI #Neuroscience #ThousandBrains #SensorimotorAI

15.08.2025 17:37 👍 5 🔁 2 💬 0 📌 0
Preview
Open-Source Software Engineer As a software engineer on the Thousand Brains Project, you will shape our open-source code base to make it accessible to a large research community. Additionally, you will write code and maintain infr...

... both about next-generation AI, as well as top-tier software development.

Flexible/remote work available.

thousandbrains.org/company/care...

(2/2)

04.08.2025 10:26 👍 3 🔁 0 💬 0 📌 0
Careers | Thousand Brains Project Join our team We believe we're building the foundations of the most exciting technology to ever exist.   Join us on this journey and work with some

Great opportunity to join our team! 🚀

If you want to be part of an initiative to develop truly robust AI alongside a group of upbeat, talented, and supportive people, do check this out.

@tristanls.bsky.social is also an amazing engineer so you will learn loads... (1/2)

04.08.2025 10:26 👍 3 🔁 0 💬 1 📌 0
2025/07 - Thousand-Brains Systems: Sensorimotor Intelligence for Rapid Robust Learning and Inference
2025/07 - Thousand-Brains Systems: Sensorimotor Intelligence for Rapid Robust Learning and Inference YouTube video by Thousand Brains Project

🎥 Watch @cortical-canonical.bsky.social present our new paper:

"Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference"

Watch the full talk here: youtu.be/3d4DmnODLnE

Sensorimotor learning implemented from 20 years of neocortex research.

15.07.2025 23:19 👍 4 🔁 1 💬 0 📌 1
Post image

1/
🚨Another New Paper Drop! 🚨 “Hierarchy or Heterarchy? A Theory of Long-Range Connections for the Sensorimotor Brain”

👇 Dive into the full thread 🧵
arxiv.org/abs/2507.05888

11.07.2025 18:35 👍 8 🔁 4 💬 1 📌 0

In case you missed it, check out our ML-focused paper on the current capabilities of Monty:
- Robust object reps w/ symmetry
- Model-free + model-based policies
- Rapid inference + learning
- Continual learning
- FLOPs efficient (8+ orders of magnitude)

bsky.app/profile/cort...

09.07.2025 18:20 👍 0 🔁 0 💬 0 📌 0

No you're not seeing double 😵😅 Today we drop a second major paper from our group - this time on neuro theory.

It covers non-hierarchical processing, transformations by the thalamus and object reps. These are already informing future versions of Monty, our sensorimotor AI.

09.07.2025 18:19 👍 4 🔁 0 💬 1 📌 0

...robust inference - all essentially for free in a system inspired by the architecture of the mammalian neocortex. If you've had the growing feeling that training transformers on an internet worth of data might not be the path to true intelligence, then this is probably for you.

08.07.2025 14:03 👍 3 🔁 0 💬 0 📌 0

Ok this is one I've been really excited to share - our pre-print demonstrating the capabilities of thousand-brain systems is now out 🧠🚀 It gives a great overview of why we believe the approach we're taking is so promising. Rapid and continual learning leading to rapid and...

08.07.2025 14:02 👍 5 🔁 2 💬 1 📌 1

With the hardware costs of robotics continuing to fall, there's never been a better time to work on sensorimotor intelligence - the missing piece for robotics to fulfill its huge potential.

Thank you to @hf.co @remicadene.bsky.social for continuing to lower barriers with open-source 🙌

27.02.2025 11:14 👍 0 🔁 0 💬 0 📌 0

@thousandbrains.org is an epic place to work with talented, humble people and interesting conversations every day 🧠 ☕ I feel very lucky to be here. Check this out if you're passionate about open-source software and developing sensorimotor intelligence.

14.02.2025 15:49 👍 1 🔁 0 💬 0 📌 0
2024/07 - Review of Biological Learning Rules
2024/07 - Review of Biological Learning Rules YouTube video by Thousand Brains Project

🚀 New Video Release! 🚀

@cortical-canonical.bsky.social presents a deep dive into learning rules in biological and deep learning neurons, covering Hebbian learning, spike timing dependent plasticity (STDP), and @numentaofficial.bsky.social's HTM neuron learning rules. 🧠🔬

youtu.be/ulkczYudXiE

30.01.2025 20:01 👍 1 🔁 1 💬 0 📌 0

Excited to announce the release of our white paper in time for the new year! If you've been looking for a more technical write-up to learn about the Thousand Brains Project and the underlying Monty system, this is a great place to start.

31.12.2024 09:51 👍 1 🔁 0 💬 0 📌 0

global output of a transformer. Together with direct sensory inputs (not isomorphic to skip connections in DNNs), this means that the cortex (and Monty) is made up of many direct sensorimotor loops, while also having a hierarchical arrangement (see also www.nature.com/articles/s41...).

12.12.2024 18:18 👍 1 🔁 0 💬 0 📌 0
Preview
How deep is the brain? The shallow brain hypothesis - Nature Reviews Neuroscience Architectures in neural networks commonly assume that inference is hierarchical. In this Perspective, Suzuki et al. present the shallow brain hypothesis, a neural processing mechanism based on ne...

One point that I didn't mention because we weren't as focused on policies in March 2023 - every cortical column in the brain, and therefore every learning module in Monty, has a direct projection to sub-cortical motor-type regions. This is very different from the final,

(1/2)

12.12.2024 18:17 👍 2 🔁 0 💬 1 📌 0

Was awesome being able to share the work we have been doing - thank you to everyone who tuned in and for all the excellent questions (over 170 👀 - we will respond to those we didn't get to soon!)

05.12.2024 16:53 👍 1 🔁 0 💬 0 📌 0

We believe the Thousand Brains Project is an exciting and fundamentally different way to build AI with structured models of the world 🌶️

Check out our symposium tomorrow if you want to hear more and ask some burning questions!

03.12.2024 10:38 👍 1 🔁 0 💬 0 📌 0
2024/10 - Overview of Action Policies in Monty, Part II - Model-Based Policies
2024/10 - Overview of Action Policies in Monty, Part II - Model-Based Policies YouTube video by Thousand Brains Project

🚀 Part 2 is here! Dive deeper into Monty’s action policies as @cortical-canonical.bsky.social breaks down model-based learning, cortical-subcortical interplay, abstract spaces, and hierarchical goal planning. Ready for insights into the future of AI? Watch now! 📽️ youtu.be/lBWV3Yw5tCI

29.11.2024 19:32 👍 7 🔁 2 💬 0 📌 0
2024/10 - Overview of Action Policies in Monty, Part I - Model-Free Policies
2024/10 - Overview of Action Policies in Monty, Part I - Model-Free Policies YouTube video by Thousand Brains Project

🚀 New video drop! @cortical-canonical.bsky.social dives into Monty’s action policies & design: from utility-based agents to model free policies. Plus, the future of modular multi-agent systems, efficient exploration and compositional objects! 🤖🌐 Watch now: www.youtube.com/watch?v=uaJG...

28.11.2024 04:27 👍 4 🔁 2 💬 0 📌 0

🚨 NEWS ALERT! Our open-source research initiative @1000brainsproj.bsky.social just publicly released its first code implementation!

We invite all researchers and developers to join us and contribute to this unique and exciting initiative.

Check out our resources below 👇

20.11.2024 14:34 👍 8 🔁 2 💬 0 📌 0

Super excited that we've gotten to this point 🙌

Can't wait to see what ideas the community comes up with. If you're interested in making fundamental advances in machine intelligence, come check it out 🧠

#opensource

20.11.2024 20:05 👍 6 🔁 1 💬 0 📌 0