# The Thousand Brains Theory 2.0: An Extension for the Long-Range Connections of the Neocortical Heterarchy

arXiv: https://arxiv.org/abs/2507.05888 · HTML: https://mlsanity.com/paper/2507.05888/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 119 references that are in the map.
- First posted on arXiv 8 Jul 2025.

## Builds on (most cited first, 10 of 10)

- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs](https://mlsanity.com/paper/1909.06161/) (2019)
- [Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex](https://mlsanity.com/paper/1511.00083/) (2015)
- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [Towards Biologically Plausible Convolutional Networks](https://mlsanity.com/paper/2106.13031/) (2021)
- [Sensitivity of Slot-Based Object-Centric Models to their Number of Slots](https://mlsanity.com/paper/2305.18890/) (2023)
- [A comparison between humans and AI at recognizing objects in unusual poses](https://mlsanity.com/paper/2402.03973/) (2024)
- [The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2411.10175/) (2024)
- [The Thousand Brains Project: A New Paradigm for Sensorimotor Intelligence](https://mlsanity.com/paper/2412.18354/) (2024)
- [Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference](https://mlsanity.com/paper/2507.04494/) (2025)

## Built on by (most cited first, 2 of 2)

- [Systems Explaining Systems: A Framework for Intelligence and Consciousness](https://mlsanity.com/paper/2601.04269/) (2026)
- [Error Highways: Scaling Predictive Coding to Very Deep Networks](https://mlsanity.com/paper/2606.22744/) (2026)

## Abstract (arXiv)

Vernon Mountcastle hypothesized that the basis for intelligence in mammals is the replication of a general computational unit, the cortical column. The Thousand Brains Theory proposed that each column is a sensorimotor system, capable of learning structured models of objects by integrating sensory input over multiple movements. Previous papers on the Thousand Brains Theory focused on the computations that occur within individual cortical columns, and how columns can use long-range connections to rapidly reach a consensus. However, several prominent long-range connection types in the neocortex were not addressed by the theory. These include hierarchical feedforward and feedback connections, as well as those that go through the thalamus. In addition, several theoretical requirements were not addressed. These include how the cortex learns compositional objects, and how information is converted from the egocentric perspective of sensors to the allocentric perspective of models in the cortex. In this paper, we extend the Thousand Brains Theory to address these issues. We begin by reviewing the anatomy of long-range neocortical connections, arguing that they form a heterarchy, rather than hierarchy, which has made their functions challenging to understand through existing theoretical models. We then propose specific roles for each of these connections. First, the thalamus converts the orientation of features and movement information from an egocentric perspective to the allocentric perspective of learned models. Second, hierarchical feedforward, feedback, and cortico-thalamo-cortical projections enable columns to learn compositional models. We discuss the relationship of our proposals to experimental findings at the levels of anatomy, neurophysiology, and behavior, along with testable predictions for future experimental work.