# Latest

**URL:** https://discourse.numenta.org/latest.md

[Latest](https://discourse.numenta.org/latest.md) · [Categories](https://discourse.numenta.org/categories.md) · [Tags](https://discourse.numenta.org/tags.md)

---

## [Creating Intelligence - A Computational Foundation for AGI](https://discourse.numenta.org/t/creating-intelligence-a-computational-foundation-for-agi/12455)

<div class="topic-metadata">

**Author:** [@POv](https://discourse.numenta.org/u/POv)\
**Replies:** 67\
**Last updated:** [September 23, 2026, 2:11pm UTC](https://discourse.numenta.org/t/creating-intelligence-a-computational-foundation-for-agi/12455 "2026-09-23T14:11:00Z")

</div>

Hi everyone, It’s been four years since my Triadic Memory project was discussed here. That topic became the most-replied-to thread on this forum, and I am still incredibly grateful for the discussions we had. Now, I’m…

---

## [The Dynamic Deficit Hypothesis: A Radical Abstraction of Self, Sensation, and Consciousness](https://discourse.numenta.org/t/the-dynamic-deficit-hypothesis-a-radical-abstraction-of-self-sensation-and-consciousness/12613)

<div class="topic-metadata">

**Author:** [@LEMA](https://discourse.numenta.org/u/LEMA)\
**Replies:** 15\
**Last updated:** [September 22, 2026, 2:08am UTC](https://discourse.numenta.org/t/the-dynamic-deficit-hypothesis-a-radical-abstraction-of-self-sensation-and-consciousness/12613 "2026-09-22T02:08:39Z")

</div>

You’d really help me out if we pick this controversial topic apart piece by piece I would like to share a controversial and speculative hypothesis regarding the nature of subjective experience. The paper, titled “The Dy…

---

## [Neural Topographic Maps & CCSLM](https://discourse.numenta.org/t/neural-topographic-maps-ccslm/12612)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 5\
**Last updated:** [September 15, 2026, 11:39pm UTC](https://discourse.numenta.org/t/neural-topographic-maps-ccslm/12612 "2026-09-15T23:39:18Z")

</div>

I recalled that there are sensory topographic maps in the brain. Why would the brain do that, unless it wanted to apply a sequence of not too drastic geometric mapping to the data? Perhaps along the lines of linear mappi…

---

## [Linear Mappings have a Memory](https://discourse.numenta.org/t/linear-mappings-have-a-memory/12585)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 9\
**Last updated:** [September 11, 2026, 3:04pm UTC](https://discourse.numenta.org/t/linear-mappings-have-a-memory/12585 "2026-09-11T15:04:39Z")

</div>

Note about the memory effects seen when you use linear mappings as associative memory. Prior memories can hang around for a long time, including random memories programmed in by random initialization. That’s because st…

---

## [Selective Self-Organization Hypothesis (GSS 1.0) An Operational Architecture of Functional Subjectivity (with Ontological Extensions)](https://discourse.numenta.org/t/selective-self-organization-hypothesis-gss-1-0-an-operational-architecture-of-functional-subjectivity-with-ontological-extensions/12583)

<div class="topic-metadata">

**Author:** [@LEMA](https://discourse.numenta.org/u/LEMA)\
**Replies:** 15\
**Last updated:** [September 11, 2026, 3:56am UTC](https://discourse.numenta.org/t/selective-self-organization-hypothesis-gss-1-0-an-operational-architecture-of-functional-subjectivity-with-ontological-extensions/12583 "2026-09-11T03:56:50Z")

</div>

I propose an alternative architecture for understanding functional subjectivity based on selective self-organization, rather than on the training methods of modern neural networks. Instead of optimizing a loss function …

---

## [Progress in the Analysis of Cortical Circuit Implementations](https://discourse.numenta.org/t/progress-in-the-analysis-of-cortical-circuit-implementations/12530)

<div class="topic-metadata">

**Author:** [@jacobeverist](https://discourse.numenta.org/u/jacobeverist)\
**Replies:** 8\
**Last updated:** [September 10, 2026, 6:28am UTC](https://discourse.numenta.org/t/progress-in-the-analysis-of-cortical-circuit-implementations/12530 "2026-09-10T06:28:54Z")

</div>

Hello all! FYI, this post is mirrored on my blog although I’m writing directly to you folks. Some time ago I coined the term Discrete Cortical Circuits and described the distinguishing characteristics that many have in…

---

## [Self-improving intelligence](https://discourse.numenta.org/t/self-improving-intelligence/5613)

<div class="topic-metadata">

**Author:** [@Paul\_Lamb](https://discourse.numenta.org/u/Paul_Lamb)\
**Replies:** 46\
**Last updated:** [September 9, 2026, 9:28pm UTC](https://discourse.numenta.org/t/self-improving-intelligence/5613 "2026-09-09T21:28:32Z")

</div>

I am attempting to create a low-level “organism” of sorts, which has all the basic components needed to control a body, form models of itself, of its world, etc. and learn to satisfy needs. This seed entity will be the…

---

## [Neuron Populations: Mathematical Structure of Data and Operations](https://discourse.numenta.org/t/neuron-populations-mathematical-structure-of-data-and-operations/12538)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 12\
**Last updated:** [September 9, 2026, 1:09pm UTC](https://discourse.numenta.org/t/neuron-populations-mathematical-structure-of-data-and-operations/12538 "2026-09-09T13:09:28Z")

</div>

This paper on the biological brain seems to fit in with the concatenated context selected linear mapping viewpoint of artificial neural networks. https://arxiv.org/html/2309.02332v3 See what you think anyway.

---

## [DCC Studio Demonstration](https://discourse.numenta.org/t/dcc-studio-demonstration/12533)

<div class="topic-metadata">

**Author:** [@jacobeverist](https://discourse.numenta.org/u/jacobeverist)\
**Replies:** 3\
**Last updated:** [August 26, 2026, 12:05pm UTC](https://discourse.numenta.org/t/dcc-studio-demonstration/12533 "2026-08-26T12:05:41Z")

</div>

For over a year now, I’ve been working hard on a web-based application for building, exploring, and learning about Discrete Cortical Circuits (DCC), which I now call the DCC Studio. It’s finally in a state where I’m com…

---

## [Explicit Context Variables for Context-Conditioned Linear Systems](https://discourse.numenta.org/t/explicit-context-variables-for-context-conditioned-linear-systems/12511)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 8\
**Last updated:** [August 17, 2026, 1:42pm UTC](https://discourse.numenta.org/t/explicit-context-variables-for-context-conditioned-linear-systems/12511 "2026-08-17T13:42:28Z")

</div>

If you think a context dependent chain of linear mappings is a good approach then you have a lot of opportunity to include context signals often seen in biological systems: https://archive.org/details/technical-note-exp…

---

## [Lessons from CCSLM for Understanding Animal Neural Networks](https://discourse.numenta.org/t/lessons-from-ccslm-for-understanding-animal-neural-networks/12529)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 0\
**Last updated:** [August 10, 2026, 3:05am UTC](https://discourse.numenta.org/t/lessons-from-ccslm-for-understanding-animal-neural-networks/12529 "2026-08-10T03:05:24Z")

</div>

Experiments and discussions around concatenated context-selected linear mapping systems suggest several constraints that may be relevant to biological neural networks. https://archive.org/details/lessons-from-concatenat…

---

## [The Thousand Brains Theory - Reviewed](https://discourse.numenta.org/t/the-thousand-brains-theory-reviewed/6528)

<div class="topic-metadata">

**Author:** [@rhyolight](https://discourse.numenta.org/u/rhyolight)\
**Replies:** 35\
**Last updated:** [August 6, 2026, 10:38am UTC](https://discourse.numenta.org/t/the-thousand-brains-theory-reviewed/6528 "2026-08-06T10:38:22Z")

</div>

Live today (soon). This is a review of A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex.

---

## [From Piecewise Linear Networks to Context Selected Linear Mappings](https://discourse.numenta.org/t/from-piecewise-linear-networks-to-context-selected-linear-mappings/12520)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 0\
**Last updated:** [August 1, 2026, 10:07pm UTC](https://discourse.numenta.org/t/from-piecewise-linear-networks-to-context-selected-linear-mappings/12520 "2026-08-01T22:07:45Z")

</div>

It is widely understood that ReLU neural networks are piece-wise linear mappings. I have tried to give an ‘almost no choice’ argument leading to a layer-wise context mechanism: From Piecewise Linear Networks to Context…

---

## [New Biologically Constrained Learning Rule](https://discourse.numenta.org/t/new-biologically-constrained-learning-rule/12291)

<div class="topic-metadata">

**Author:** [@dmac](https://discourse.numenta.org/u/dmac)\
**Replies:** 1\
**Last updated:** [July 28, 2026, 2:25pm UTC](https://discourse.numenta.org/t/new-biologically-constrained-learning-rule/12291 "2026-07-28T14:25:47Z")

</div>

A generalized mathematical framework for the calcium control hypothesis describes weight‐dependent synaptic plasticity Toviah Moldwin, Li Shay Azran, Idan Segev (2025) https://doi.org/10.1007/s10827-025-00894-6 Abstra…

---

## [Real Neuro-Symbolic AI - BrainStem\_V8 Needs to Sleep](https://discourse.numenta.org/t/real-neuro-symbolic-ai-brainstem-v8-needs-to-sleep/12515)

<div class="topic-metadata">

**Author:** [@unikum-sol](https://discourse.numenta.org/u/unikum-sol)\
**Replies:** 0\
**Last updated:** [July 28, 2026, 1:35pm UTC](https://discourse.numenta.org/t/real-neuro-symbolic-ai-brainstem-v8-needs-to-sleep/12515 "2026-07-28T13:35:26Z")

</div>

Why the Next Generation of AI Needs to Sleep: 5 Surprising Lessons from Bio-Digital Brains. RNS-AI Current artificial intelligence architectures face a profound existential hurdle: the “hallucination” problem. These…

---

## [Topological Harmonic Cognition](https://discourse.numenta.org/t/topological-harmonic-cognition/12387)

<div class="topic-metadata">

**Author:** [@Davis\_Sai](https://discourse.numenta.org/u/Davis_Sai)\
**Replies:** 12\
**Last updated:** [July 23, 2026, 5:43pm UTC](https://discourse.numenta.org/t/topological-harmonic-cognition/12387 "2026-07-23T17:43:20Z")

</div>

Topological Harmonic Cognition: Variational Deficit Resolution on Co-Evolving Neural Cellular Automata abstract ===== We propose a theory of cognition and reasoning based on a dynamically self-reconfiguring Neural Cel…

---

## [Context Dependent Composition Of Linear Operators](https://discourse.numenta.org/t/context-dependent-composition-of-linear-operators/12510)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 0\
**Last updated:** [July 22, 2026, 11:54pm UTC](https://discourse.numenta.org/t/context-dependent-composition-of-linear-operators/12510 "2026-07-22T23:54:09Z")

</div>

I made an effort to express in a comprehensible way some ideas I have about context dependent composition of linear operators: https://archive.org/details/context-dependent-composition-of-linear-operators The funny thi…

---

## [Feedback wanted: Hobbist-built Codec for Large Sparse Binary Vectors](https://discourse.numenta.org/t/feedback-wanted-hobbist-built-codec-for-large-sparse-binary-vectors/12507)

<div class="topic-metadata">

**Author:** [@Nik\_Bielski](https://discourse.numenta.org/u/Nik_Bielski)\
**Replies:** 3\
**Last updated:** [July 21, 2026, 10:47am UTC](https://discourse.numenta.org/t/feedback-wanted-hobbist-built-codec-for-large-sparse-binary-vectors/12507 "2026-07-21T10:47:47Z")

</div>

My cousins and I have been developing a new codec for very large sparse binary vectors, and the initial results seems promising for parameter free encodings. Initially we thought it might be pretty novel, because the cod…

---

## [BDH (Baby Dragon Hatchling)](https://discourse.numenta.org/t/bdh-baby-dragon-hatchling/12185)

<div class="topic-metadata">

**Author:** [@MTIzNDU2Nzg5](https://discourse.numenta.org/u/MTIzNDU2Nzg5)\
**Replies:** 4\
**Last updated:** [July 21, 2026, 10:37am UTC](https://discourse.numenta.org/t/bdh-baby-dragon-hatchling/12185 "2026-07-21T10:37:30Z")

</div>

Https://arxiv.org/pdf/2509.26507 This paper on BDH (Baby Dragon Hatchling). It’s basically an attempt to replace the Transformer bottleneck with a scale-free graph of “neuron particles.” The technical gist: No KV Ca…

---

## [State of Brain Emulation Report 2025](https://discourse.numenta.org/t/state-of-brain-emulation-report-2025/12467)

<div class="topic-metadata">

**Author:** [@dmac](https://discourse.numenta.org/u/dmac)\
**Replies:** 1\
**Last updated:** [July 19, 2026, 9:04am UTC](https://discourse.numenta.org/t/state-of-brain-emulation-report-2025/12467 "2026-07-19T09:04:03Z")

</div>

State of Brain Emulation Report 2025 A comprehensive report of the current status of whole-brain simulation. This focuses on five model organisms (c. elegans, larval zebrafish, drosophilia, mouse, human).

---

## [Context based learning and the best average linear mapping](https://discourse.numenta.org/t/context-based-learning-and-the-best-average-linear-mapping/12465)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 3\
**Last updated:** [July 16, 2026, 10:34pm UTC](https://discourse.numenta.org/t/context-based-learning-and-the-best-average-linear-mapping/12465 "2026-07-16T22:34:12Z")

</div>

Given a context at each layer that selects parameters for a linear mapping, training produces the best average linear mapping for that context. Then the entire networks is a composition of best average linear mappings. …

---

## [The Triad of Context Driven Learning](https://discourse.numenta.org/t/the-triad-of-context-driven-learning/12458)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 1\
**Last updated:** [July 8, 2026, 12:35pm UTC](https://discourse.numenta.org/t/the-triad-of-context-driven-learning/12458 "2026-07-08T12:35:57Z")

</div>

I wrote up some details of context driven learning in as simple a way as I could: https://archive.org/details/triad-of-context-driven-learning The triad is: Context Conditional computing Learning

---

## [Atlas LSH neural networks](https://discourse.numenta.org/t/atlas-lsh-neural-networks/12457)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 5\
**Last updated:** [July 3, 2026, 12:32am UTC](https://discourse.numenta.org/t/atlas-lsh-neural-networks/12457 "2026-07-03T00:32:16Z")

</div>

I’ve been exploring some ideas about locality sensitive hash based neural networks. https://archive.org/details/atlas-lsh-neural-networks-an-intuitive-overview You can click on “uploaded by” for more information.

---

## [Cognitive Coherence Model (CCM - A cognitive standalone architecture)](https://discourse.numenta.org/t/cognitive-coherence-model-ccm-a-cognitive-standalone-architecture/12451)

<div class="topic-metadata">

**Author:** [@Akimsa\_3](https://discourse.numenta.org/u/Akimsa_3)\
**Replies:** 0\
**Last updated:** [June 17, 2026, 9:31pm UTC](https://discourse.numenta.org/t/cognitive-coherence-model-ccm-a-cognitive-standalone-architecture/12451 "2026-06-17T21:31:30Z")

</div>

Hi everybody i’m Akimsa3 the creator of the CCM (Cognitive Coherence Model). A standalone cognitive architecture that tries to aim to replicate cognitive process beyond a single channel, now it has an early build impleme…

---

## [SDR transformer live training](https://discourse.numenta.org/t/sdr-transformer-live-training/12450)

<div class="topic-metadata">

**Author:** [@aamir121a](https://discourse.numenta.org/u/aamir121a)\
**Replies:** 0\
**Last updated:** [June 12, 2026, 1:08pm UTC](https://discourse.numenta.org/t/sdr-transformer-live-training/12450 "2026-06-12T13:08:34Z")

</div>

Training a 2 bit SDR transformer , SDR learns the mapping of 'Internet to ’ ‘Usage’ Prompt: \[The internet is\] Generated: \[ available to millions by making such strong connections. The network encompasses the func…

---

## [Random Projection Sub-Sampling and Restoration](https://discourse.numenta.org/t/random-projection-sub-sampling-and-restoration/12431)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 2\
**Last updated:** [May 27, 2026, 5:08am UTC](https://discourse.numenta.org/t/random-projection-sub-sampling-and-restoration/12431 "2026-05-27T05:08:19Z")

</div>

One thing I noticed experimenting with associative memory is splitting the data into 2 information orthogonal paths improved the results a lot. Therefore why not split it into multiple orthogonal paths using say random …

---

## [Why do members here think DL-based methods can't achieve AGI?](https://discourse.numenta.org/t/why-do-members-here-think-dl-based-methods-cant-achieve-agi/9253)

<div class="topic-metadata">

**Author:** [@neel\_g](https://discourse.numenta.org/u/neel_g)\
**Replies:** 182\
**Last updated:** [May 23, 2026, 2:37am UTC](https://discourse.numenta.org/t/why-do-members-here-think-dl-based-methods-cant-achieve-agi/9253 "2026-05-23T02:37:14Z")

</div>

It’s very interesting to observe members here discussing about TBT (which I will declare beforehand I know very little of, along with neuroscience). I am concerned, however, with the parallel of approaches taken by Deep…

---

## [Visualizing Properties of Encoders](https://discourse.numenta.org/t/visualizing-properties-of-encoders/10727)

<div class="topic-metadata">

**Author:** [@jacobeverist](https://discourse.numenta.org/u/jacobeverist)\
**Replies:** 34\
**Last updated:** [May 13, 2026, 5:52am UTC](https://discourse.numenta.org/t/visualizing-properties-of-encoders/10727 "2026-05-13T05:52:18Z")

</div>

One of the biggest unspoken challenges I had when exploring HTM theory and trying to build applications was: how do you choose and configure encoders to translate your raw input data into SDRs? This problem has been ack…

---

## [Column/assembly graph neural network](https://discourse.numenta.org/t/column-assembly-graph-neural-network/12345)

<div class="topic-metadata">

**Author:** [@richardbaxter](https://discourse.numenta.org/u/richardbaxter)\
**Replies:** 4\
**Last updated:** [May 13, 2026, 5:20am UTC](https://discourse.numenta.org/t/column-assembly-graph-neural-network/12345 "2026-05-13T05:20:36Z")

</div>

I have created a knowledgebase/graph neural network architecture (GIAANN prototype) which can be used to predict the next token in a sequence. It trains a set of columns for every new noun encountered in a textual corpus…

---

## [Exploring cognitive skill profiles through training task performance](https://discourse.numenta.org/t/exploring-cognitive-skill-profiles-through-training-task-performance/12373)

<div class="topic-metadata">

**Author:** [@Emir\_Baycan](https://discourse.numenta.org/u/Emir_Baycan)\
**Replies:** 0\
**Last updated:** [May 12, 2026, 3:27am UTC](https://discourse.numenta.org/t/exploring-cognitive-skill-profiles-through-training-task-performance/12373 "2026-05-12T03:27:04Z")

</div>

We’ve been building an online cognitive testing platform and recently expanded it with a separate training section focused on specific cognitive functions rather than only IQ scoring. One interesting pattern we kept not…

[Next page](https://discourse.numenta.org/latest.md?page=1)