# Latest

**URL:** https://discourse.numenta.org/latest.md?page=5

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

**Page:** 6

---

## [Paper on combining "cortical" WTA with transformers](https://discourse.numenta.org/t/paper-on-combining-cortical-wta-with-transformers/11562)

<div class="topic-metadata">

**Author:** [@bkaz](https://discourse.numenta.org/u/bkaz)\
**Replies:** 3\
**Last updated:** [October 26, 2024, 8:35pm UTC](https://discourse.numenta.org/t/paper-on-combining-cortical-wta-with-transformers/11562 "2024-10-26T20:35:57Z")

</div>

I guess this is similar to spatial pooling in HTM? “Winner-take-all” is a biological mechanism that occurs when one or a few neurons within a set (i.e., the one/ones with the highest activation level) influence the o…

---

## [The Holy-hardware grail of brain-emulating AI seems attainable](https://discourse.numenta.org/t/the-holy-hardware-grail-of-brain-emulating-ai-seems-attainable/11568)

<div class="topic-metadata">

**Author:** [@Peter2](https://discourse.numenta.org/u/Peter2)\
**Replies:** 0\
**Last updated:** [October 26, 2024, 12:38am UTC](https://discourse.numenta.org/t/the-holy-hardware-grail-of-brain-emulating-ai-seems-attainable/11568 "2024-10-26T00:38:27Z")

</div>

---

## [Crafting a Reward Function with a Heir-achy of Needs for Complex Goal Formation](https://discourse.numenta.org/t/crafting-a-reward-function-with-a-heir-achy-of-needs-for-complex-goal-formation/11566)

<div class="topic-metadata">

**Author:** [@Tofara\_Moyo](https://discourse.numenta.org/u/Tofara_Moyo)\
**Replies:** 0\
**Last updated:** [October 26, 2024, 12:16am UTC](https://discourse.numenta.org/t/crafting-a-reward-function-with-a-heir-achy-of-needs-for-complex-goal-formation/11566 "2024-10-26T00:16:17Z")

</div>

Crafting a Reward Function with a Heir-achy of Needs for Complex Goal Formation author tofara moyo abstract We show a simple method for an agent to learn levels of abstractions ordered by priority that ultimately incre…

---

## [Symbol Based Self Guided Neural Architecture Search in a Spiking Neural Network](https://discourse.numenta.org/t/symbol-based-self-guided-neural-architecture-search-in-a-spiking-neural-network/11563)

<div class="topic-metadata">

**Author:** [@Tofara\_Moyo](https://discourse.numenta.org/u/Tofara_Moyo)\
**Replies:** 0\
**Last updated:** [October 25, 2024, 10:01pm UTC](https://discourse.numenta.org/t/symbol-based-self-guided-neural-architecture-search-in-a-spiking-neural-network/11563 "2024-10-25T22:01:24Z")

</div>

Symbol Based Self Guided Neural Architecture Search in a Spiking Neural Network author Tofara Moyo abstract A spiking neural networks neurons can viewed as feature detectors or alternatively instances of hieroglyphic s…

---

## [Jeff Hawkins Interview on "Inner Cosmos with David Eagleman"](https://discourse.numenta.org/t/jeff-hawkins-interview-on-inner-cosmos-with-david-eagleman/11556)

<div class="topic-metadata">

**Author:** [@CollinsEM](https://discourse.numenta.org/u/CollinsEM)\
**Replies:** 1\
**Last updated:** [October 22, 2024, 10:16pm UTC](https://discourse.numenta.org/t/jeff-hawkins-interview-on-inner-cosmos-with-david-eagleman/11556 "2024-10-22T22:16:45Z")

</div>

Latest interview with Jeff Hawkins on the “Inner Cosmos” podcast. Includes an update on the status of the Thousand-Brains Project at about 39:00 minutes.

---

## [Creating intelligence may require only exposure to complexity](https://discourse.numenta.org/t/creating-intelligence-may-require-only-exposure-to-complexity/11561)

<div class="topic-metadata">

**Author:** [@roboto](https://discourse.numenta.org/u/roboto)\
**Replies:** 0\
**Last updated:** [October 11, 2024, 12:36pm UTC](https://discourse.numenta.org/t/creating-intelligence-may-require-only-exposure-to-complexity/11561 "2024-10-11T12:36:35Z")

</div>

Just sharing some interesting transformer based research that ties in intelligence to complexity. The research states that “intelligence arises from the ability to predict complexity and that creating intelligence may…

---

## [Is this community dead? I don't see many new posts](https://discourse.numenta.org/t/is-this-community-dead-i-dont-see-many-new-posts/11493)

<div class="topic-metadata">

**Author:** [@flajann2](https://discourse.numenta.org/u/flajann2)\
**Replies:** 5\
**Last updated:** [October 7, 2024, 1:27am UTC](https://discourse.numenta.org/t/is-this-community-dead-i-dont-see-many-new-posts/11493 "2024-10-07T01:27:54Z")

</div>

It seems that the most recent posts – outside of the handful I’ve made – are from 2023. And the Discord forum seems to have past to the Great Beyond shortly after Matt did – may he rest in peace. If there is a new venue …

---

## [Future NUPIC work is closed source?](https://discourse.numenta.org/t/future-nupic-work-is-closed-source/11506)

<div class="topic-metadata">

**Author:** [@ivanislav](https://discourse.numenta.org/u/ivanislav)\
**Replies:** 3\
**Last updated:** [October 5, 2024, 11:17pm UTC](https://discourse.numenta.org/t/future-nupic-work-is-closed-source/11506 "2024-10-05T23:17:16Z")

</div>

I infer from the lack of github activity and renaming repositories as “legacy” that future work by Numenta is closed source. Does anyone know whether that’s true? On the numenta website is a link to https://github.com/n…

---

## [Anybody hear about this ? Sounds like Sensory Motor Learning to me from Thousand Brains Theory](https://discourse.numenta.org/t/anybody-hear-about-this-sounds-like-sensory-motor-learning-to-me-from-thousand-brains-theory/11550)

<div class="topic-metadata">

**Author:** [@Deric\_Pinto](https://discourse.numenta.org/u/Deric_Pinto)\
**Replies:** 0\
**Last updated:** [September 30, 2024, 2:33pm UTC](https://discourse.numenta.org/t/anybody-hear-about-this-sounds-like-sensory-motor-learning-to-me-from-thousand-brains-theory/11550 "2024-09-30T14:33:58Z")

</div>

Fei Fei Li - a renowned figure in the world of Computer Vision started a new company

---

## [I want advice on Using HTM for Anomaly Detection in Streaming Data](https://discourse.numenta.org/t/i-want-advice-on-using-htm-for-anomaly-detection-in-streaming-data/11544)

<div class="topic-metadata">

**Author:** [@nixiekhf](https://discourse.numenta.org/u/nixiekhf)\
**Replies:** 0\
**Last updated:** [September 26, 2024, 12:00pm UTC](https://discourse.numenta.org/t/i-want-advice-on-using-htm-for-anomaly-detection-in-streaming-data/11544 "2024-09-26T12:00:14Z")

</div>

Hi everyone, I am working on a project where I need to implement an anomaly detection system for streaming data. After exploring several approaches, I came across Hierarchical Temporal Memory & its potential for detecti…

---

## [SDR Implimentation of neural network Layers](https://discourse.numenta.org/t/sdr-implimentation-of-neural-network-layers/11521)

<div class="topic-metadata">

**Author:** [@LALAK\_YADAV](https://discourse.numenta.org/u/LALAK_YADAV)\
**Replies:** 5\
**Last updated:** [September 24, 2024, 12:15pm UTC](https://discourse.numenta.org/t/sdr-implimentation-of-neural-network-layers/11521 "2024-09-24T12:15:45Z")

</div>

I’ve been trying to apply Sparse Distributed Representations (SDR) to simple neural network layers. Can anyone suggest a method for achieving this? I want to ensure that only 2-5% of the neurons are active in each layer. …

---

## [Missing cortical column concept in some papers](https://discourse.numenta.org/t/missing-cortical-column-concept-in-some-papers/11509)

<div class="topic-metadata">

**Author:** [@ivanislav](https://discourse.numenta.org/u/ivanislav)\
**Replies:** 1\
**Last updated:** [September 22, 2024, 7:24pm UTC](https://discourse.numenta.org/t/missing-cortical-column-concept-in-some-papers/11509 "2024-09-22T19:24:04Z")

</div>

In earlier papers (2016), cortical columns were an important concept and they were explicitly modeled. In particular, only one cell would be activated at a time (for learned sequences) within a cortical column. However, …

---

## [HTM Teacher](https://discourse.numenta.org/t/htm-teacher/11516)

<div class="topic-metadata">

**Author:** [@MTIzNDU2Nzg5](https://discourse.numenta.org/u/MTIzNDU2Nzg5)\
**Replies:** 4\
**Last updated:** [September 20, 2024, 2:02am UTC](https://discourse.numenta.org/t/htm-teacher/11516 "2024-09-20T02:02:33Z")

</div>

I have always wanted to see a super slim version of HTM implementation that has output to show how it might work, but my coding skill is zero. Just create this with ChatGPT o1-preview in a few minutes.

---

## [Evolutionary Algorithms Review](https://discourse.numenta.org/t/evolutionary-algorithms-review/11088)

<div class="topic-metadata">

**Author:** [@dmac](https://discourse.numenta.org/u/dmac)\
**Replies:** 16\
**Last updated:** [September 18, 2024, 1:29pm UTC](https://discourse.numenta.org/t/evolutionary-algorithms-review/11088 "2024-09-18T13:29:37Z")

</div>

I’d like to present three articles on the topic of evolutionary algorithms. All three were co-authored by Kenneth O. Stanley, and I found them on his personal homepage: https://www.cs.ucf.edu/~kstanley/. This first …

---

## [Network model with internal complexity bridges artificial intelligence and neuroscience](https://discourse.numenta.org/t/network-model-with-internal-complexity-bridges-artificial-intelligence-and-neuroscience/11508)

<div class="topic-metadata">

**Author:** [@bkaz](https://discourse.numenta.org/u/bkaz)\
**Replies:** 0\
**Last updated:** [September 7, 2024, 2:35am UTC](https://discourse.numenta.org/t/network-model-with-internal-complexity-bridges-artificial-intelligence-and-neuroscience/11508 "2024-09-07T02:35:26Z")

</div>

https://www.nature.com/articles/s43588-024-00674-9.epdf?sharing\_token=PDLs9wc2VUGXIKvqN06zfdRgN0jAjWel9jnR3ZoTv0Pq1mNu95lhgDdNLRemgORPlbUML5QJh76FSIWzN1bZzztDfA77dZtN6Xq-bS7iRskEyi70hTTox4PALMs14Cb2ZO8Lk3x3WVQzYTznt8VqEf…

---

## [Ex-OpenAI Founder Ilya Sutskever Strikes Back!](https://discourse.numenta.org/t/ex-openai-founder-ilya-sutskever-strikes-back/11504)

<div class="topic-metadata">

**Author:** [@MTIzNDU2Nzg5](https://discourse.numenta.org/u/MTIzNDU2Nzg5)\
**Replies:** 0\
**Last updated:** [September 5, 2024, 8:52pm UTC](https://discourse.numenta.org/t/ex-openai-founder-ilya-sutskever-strikes-back/11504 "2024-09-05T20:52:22Z")

</div>

Numenta should join this.

---

## [Open Invitation for Fellow HTM Enthusiasts for collaboration](https://discourse.numenta.org/t/open-invitation-for-fellow-htm-enthusiasts-for-collaboration/11497)

<div class="topic-metadata">

**Author:** [@Deric\_Pinto](https://discourse.numenta.org/u/Deric_Pinto)\
**Replies:** 2\
**Last updated:** [September 5, 2024, 12:48am UTC](https://discourse.numenta.org/t/open-invitation-for-fellow-htm-enthusiasts-for-collaboration/11497 "2024-09-05T00:48:34Z")

</div>

Project: A self-navigating Agent capable of perception and building a 2D spatial Map of its environment. Blog: https://decision-machines.com/blogs/f/brain-based-spatial-navigation Project Description: The project invo…

---

## [A Invitation](https://discourse.numenta.org/t/a-invitation/11500)

<div class="topic-metadata">

**Author:** [@Prakash](https://discourse.numenta.org/u/Prakash)\
**Replies:** 0\
**Last updated:** [September 3, 2024, 1:45pm UTC](https://discourse.numenta.org/t/a-invitation/11500 "2024-09-03T13:45:37Z")

</div>

I am working on a project, it was based on converting my theory about how the brain works into a code. I have made the code that runs, but it has to be improved more to get the correct output. I need your help on improvi…

---

## [Clone-structured cognitive graphs (CSCG)](https://discourse.numenta.org/t/clone-structured-cognitive-graphs-cscg/9739)

<div class="topic-metadata">

**Author:** [@fcred](https://discourse.numenta.org/u/fcred)\
**Replies:** 9\
**Last updated:** [August 15, 2024, 12:43pm UTC](https://discourse.numenta.org/t/clone-structured-cognitive-graphs-cscg/9739 "2024-08-15T12:43:37Z")

</div>

I do not know if everyone is familiar with Dileep George’s paper Clone-structured graph representations enable flexible learning and vicarious evaluation of cognitive maps. In any case, he recently gave a seminar at the…

---

## [HTM-SP paper](https://discourse.numenta.org/t/htm-sp-paper/11442)

<div class="topic-metadata">

**Author:** [@shiva\_sanati](https://discourse.numenta.org/u/shiva_sanati)\
**Replies:** 2\
**Last updated:** [August 14, 2024, 11:52pm UTC](https://discourse.numenta.org/t/htm-sp-paper/11442 "2024-08-14T23:52:32Z")

</div>

Hello, I have written two articles with the following titles: “Information-theoretic analysis of Hierarchical Temporal Memory-Spatial Pooler algorithm with a new upper bound for the standard information bottleneck met…

---

## [Multidirectional propagation of biological neurons - could/should we recreate it e.g. with joint distribution neurons?](https://discourse.numenta.org/t/multidirectional-propagation-of-biological-neurons-could-should-we-recreate-it-e-g-with-joint-distribution-neurons/11357)

<div class="topic-metadata">

**Author:** [@Jarek\_Duda](https://discourse.numenta.org/u/Jarek_Duda)\
**Replies:** 16\
**Last updated:** [August 11, 2024, 3:14pm UTC](https://discourse.numenta.org/t/multidirectional-propagation-of-biological-neurons-could-should-we-recreate-it-e-g-with-joint-distribution-neurons/11357 "2024-08-11T15:14:08Z")

</div>

While ANNs are rather trained for unidirectional propagation, action potential propagation in biological neurons is symmetric e.g. ”it is not uncommon for axonal propagation of action potentials to happen in both directi…

---

## [The principles of intelligence and cognition: John Vervaeke lays down the philosophical compass for defining AGI](https://discourse.numenta.org/t/the-principles-of-intelligence-and-cognition-john-vervaeke-lays-down-the-philosophical-compass-for-defining-agi/10722)

<div class="topic-metadata">

**Author:** [@BrainConstellation](https://discourse.numenta.org/u/BrainConstellation)\
**Replies:** 14\
**Last updated:** [August 4, 2024, 9:57am UTC](https://discourse.numenta.org/t/the-principles-of-intelligence-and-cognition-john-vervaeke-lays-down-the-philosophical-compass-for-defining-agi/10722 "2024-08-04T09:57:32Z")

</div>

If identifying the innate properties of universal forms of intelligence is a prerequisite to attain it, then this talk is one we should pay attention to. John Versaeke has a phenomenal ability to explain the principal c…

---

## [Google's Sparse Autoencoder](https://discourse.numenta.org/t/googles-sparse-autoencoder/11439)

<div class="topic-metadata">

**Author:** [@CollinsEM](https://discourse.numenta.org/u/CollinsEM)\
**Replies:** 0\
**Last updated:** [August 3, 2024, 12:42pm UTC](https://discourse.numenta.org/t/googles-sparse-autoencoder/11439 "2024-08-03T12:42:41Z")

</div>

New research from Google. Apparently they are coming around to sparse representations.

---

## [Looking for Guidance on Applying Hierarchical Temporal Memory (HTM) to IoT Data Anomaly Detection](https://discourse.numenta.org/t/looking-for-guidance-on-applying-hierarchical-temporal-memory-htm-to-iot-data-anomaly-detection/11436)

<div class="topic-metadata">

**Author:** [@Andro](https://discourse.numenta.org/u/Andro)\
**Replies:** 0\
**Last updated:** [July 23, 2024, 8:02am UTC](https://discourse.numenta.org/t/looking-for-guidance-on-applying-hierarchical-temporal-memory-htm-to-iot-data-anomaly-detection/11436 "2024-07-23T08:02:13Z")

</div>

Hello Everyone :hugs:, At present, I am engaged in a project that utilises Hierarchical Temporal Memory (HTM) that to detect anomalies in Internet of Things (IoT) data. As you may already be aware, conventional anomaly …

---

## [Remap encodings and still leverage all prior training?](https://discourse.numenta.org/t/remap-encodings-and-still-leverage-all-prior-training/11434)

<div class="topic-metadata">

**Author:** [@ediril](https://discourse.numenta.org/u/ediril)\
**Replies:** 3\
**Last updated:** [July 23, 2024, 12:31am UTC](https://discourse.numenta.org/t/remap-encodings-and-still-leverage-all-prior-training/11434 "2024-07-23T00:31:26Z")

</div>

Is it possible to remap existing encodings in such a way to keep all prior trainings? Why would I do this? Let’s say you have a bunch of encodings already and you trained an SDR with it. And then you needed to create a b…

---

## [New to 1000brains...Questions:](https://discourse.numenta.org/t/new-to-1000brains-questions/11427)

<div class="topic-metadata">

**Author:** [@arunvishwa23](https://discourse.numenta.org/u/arunvishwa23)\
**Replies:** 1\
**Last updated:** [July 12, 2024, 9:40pm UTC](https://discourse.numenta.org/t/new-to-1000brains-questions/11427 "2024-07-12T21:40:33Z")

</div>

I looked at the BaMI pdf containing the pseudocode of HTM algorithm. Am I right to say that the book version calls a “column” as a set of 4 cells and a region as a set of several “columns”? The terminology is confusing,…

---

## [Big Announcement from Numenta Later Today](https://discourse.numenta.org/t/big-announcement-from-numenta-later-today/11372)

<div class="topic-metadata">

**Author:** [@vclay](https://discourse.numenta.org/u/vclay)\
**Replies:** 23\
**Last updated:** [June 27, 2024, 3:36pm UTC](https://discourse.numenta.org/t/big-announcement-from-numenta-later-today/11372 "2024-06-27T15:36:54Z")

</div>

Hey everyone! I know you haven’t been hearing much from Numenta lately but I am excited to say that this is about to change. Later today Jeff Hawkins will give a talk at an event by the Stanford Institute for Human-Cente…

---

## [Code to measure the accuracy in HTM.Core](https://discourse.numenta.org/t/code-to-measure-the-accuracy-in-htm-core/11408)

<div class="topic-metadata">

**Author:** [@Shwetha\_Vittal](https://discourse.numenta.org/u/Shwetha_Vittal)\
**Replies:** 0\
**Last updated:** [June 17, 2024, 10:30am UTC](https://discourse.numenta.org/t/code-to-measure-the-accuracy-in-htm-core/11408 "2024-06-17T10:30:16Z")

</div>

Hi, I have been trying to use HTM.Core for one of the works in 5G Network slicing anomaly detection. For this, I have followed the example of hotgym.py. I want to capture the accuracy of anomaly detection overall. Thoug…

---

## [The 2024 Kavli Prize in Neuroscience](https://discourse.numenta.org/t/the-2024-kavli-prize-in-neuroscience/11406)

<div class="topic-metadata">

**Author:** [@EEProf](https://discourse.numenta.org/u/EEProf)\
**Replies:** 0\
**Last updated:** [June 15, 2024, 5:42pm UTC](https://discourse.numenta.org/t/the-2024-kavli-prize-in-neuroscience/11406 "2024-06-15T17:42:36Z")

</div>

I found this announcement particularly interesting given the whole “finger touching the cup” thing. Over several years of experiments, Kanwisher and her colleagues explored just how selective the fusiform face area is …

---

## [Another way to combine HTM and LLM](https://discourse.numenta.org/t/another-way-to-combine-htm-and-llm/11403)

<div class="topic-metadata">

**Author:** [@Mark\_Springer](https://discourse.numenta.org/u/Mark_Springer)\
**Replies:** 0\
**Last updated:** [June 12, 2024, 10:59am UTC](https://discourse.numenta.org/t/another-way-to-combine-htm-and-llm/11403 "2024-06-12T10:59:09Z")

</div>

I haven’t looked at the Numenta site for years, and I came up with the following idea this morning before realizing that Numenta is already working with LLMs. But here’s the idea: A way of combining Numenta’s HTM with O…

[Previous page](https://discourse.numenta.org/latest.md?page=4)

[Next page](https://discourse.numenta.org/latest.md?page=6)