# \#question

**URL:** https://discourse.numenta.org/tag/question/20.md

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

---

## [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…

---

## [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…

---

## [Using HTM for logical deduction/induction and prediction of sentences](https://discourse.numenta.org/t/using-htm-for-logical-deduction-induction-and-prediction-of-sentences/12195)

<div class="topic-metadata">

**Author:** [@Aidan\_Busby](https://discourse.numenta.org/u/Aidan_Busby)\
**Replies:** 8\
**Last updated:** [January 27, 2026, 2:35pm UTC](https://discourse.numenta.org/t/using-htm-for-logical-deduction-induction-and-prediction-of-sentences/12195 "2026-01-27T14:35:14Z")

</div>

Hello all, I have recently been experimenting with the HTM.core code to train an HTM network to learn the logic behind a corpus of sentences. Currently, they look like this: “If A is in X, where is A?” Here is my trai…

---

## [SDR classification](https://discourse.numenta.org/t/sdr-classification/12177)

<div class="topic-metadata">

**Author:** [@spitfire](https://discourse.numenta.org/u/spitfire)\
**Replies:** 27\
**Last updated:** [January 11, 2026, 1:49am UTC](https://discourse.numenta.org/t/sdr-classification/12177 "2026-01-11T01:49:50Z")

</div>

Hi, I’m trying to building a swipe keyboard recognizer. My data has Time, X, Y stroke recordings. So I can either give a timeseries, or a 2d image between each word. I also have a labeled dictionary to go with stroke …

---

## [Open-source text SDR encoder?](https://discourse.numenta.org/t/open-source-text-sdr-encoder/12127)

<div class="topic-metadata">

**Author:** [@sean](https://discourse.numenta.org/u/sean)\
**Replies:** 10\
**Last updated:** [December 22, 2025, 1:30pm UTC](https://discourse.numenta.org/t/open-source-text-sdr-encoder/12127 "2025-12-22T13:30:50Z")

</div>

Anyone knows of an open-source SDR encoder for text (ideally multilingual)? I am cooking sth. up myself using bag of words and self-organizing maps but would like to see existing methods

---

## [Could Someone Give me Advice on Implementing HTM for Real-Time Anomaly Detection in Industrial IoT Systems?](https://discourse.numenta.org/t/could-someone-give-me-advice-on-implementing-htm-for-real-time-anomaly-detection-in-industrial-iot-systems/11491)

<div class="topic-metadata">

**Author:** [@roberrttt](https://discourse.numenta.org/u/roberrttt)\
**Replies:** 2\
**Last updated:** [September 13, 2025, 11:51pm UTC](https://discourse.numenta.org/t/could-someone-give-me-advice-on-implementing-htm-for-real-time-anomaly-detection-in-industrial-iot-systems/11491 "2025-09-13T23:51:24Z")

</div>

Hello there, I am currently working on a project that involves implementing Hierarchical Temporal Memory for real time anomaly detection in an Industrial Internet of Things system. The goal is to monitor sensor data fr…

---

## [Using a Classifier with htm.core for Skeleton-Based Human Activity Recognition](https://discourse.numenta.org/t/using-a-classifier-with-htm-core-for-skeleton-based-human-activity-recognition/11889)

<div class="topic-metadata">

**Author:** [@muhammadzulqarnain58](https://discourse.numenta.org/u/muhammadzulqarnain58)\
**Replies:** 2\
**Last updated:** [September 5, 2025, 4:48am UTC](https://discourse.numenta.org/t/using-a-classifier-with-htm-core-for-skeleton-based-human-activity-recognition/11889 "2025-09-05T04:48:01Z")

</div>

Hello Everyone, I am working on a research project involving Human Activity Recognition using the NTU RGB+D 3D skeleton dataset, and I am currently building a pipeline with htm.core to process the skeletal data. So far,…

---

## [Connecting Layers in HTM.core](https://discourse.numenta.org/t/connecting-layers-in-htm-core/9890)

<div class="topic-metadata">

**Author:** [@altshiftj](https://discourse.numenta.org/u/altshiftj)\
**Replies:** 9\
**Last updated:** [July 5, 2022, 8:25am UTC](https://discourse.numenta.org/t/connecting-layers-in-htm-core/9890 "2022-07-05T08:25:53Z")

</div>

Hey Everybody, I am currently working on a ‘mouse in the box’ experiment with htm.core. That is, a ‘mouse’ moves randomly in a box and has vision sensing. I encode and pool vision both spatially and temporaly to create…

---

## [Application of HTM algorithm](https://discourse.numenta.org/t/application-of-htm-algorithm/11826)

<div class="topic-metadata">

**Author:** [@arunvishwa23](https://discourse.numenta.org/u/arunvishwa23)\
**Replies:** 6\
**Last updated:** [May 2, 2025, 3:09pm UTC](https://discourse.numenta.org/t/application-of-htm-algorithm/11826 "2025-05-02T15:09:50Z")

</div>

Has anyone tried to use HTM algorithm to learn the language (effectively like a language model)? Just curious to know if anyone has attempted in that direction (or in general NLP). Thanks.

---

## [Submit to AGI conference or Neurips](https://discourse.numenta.org/t/submit-to-agi-conference-or-neurips/11769)

<div class="topic-metadata">

**Author:** [@Tofara\_Moyo](https://discourse.numenta.org/u/Tofara_Moyo)\
**Replies:** 5\
**Last updated:** [March 14, 2025, 8:10pm UTC](https://discourse.numenta.org/t/submit-to-agi-conference-or-neurips/11769 "2025-03-14T20:10:32Z")

</div>

Hi, I was wondering which it is better to present at for exposure. AGI conference or Neurips? I suppose that neurips is more prestigious, but i fear focus being taken away by other non agi related content. On the other …

---

## [How to get started in Brain Based AI?](https://discourse.numenta.org/t/how-to-get-started-in-brain-based-ai/10757)

<div class="topic-metadata">

**Author:** [@ajaynaidu](https://discourse.numenta.org/u/ajaynaidu)\
**Replies:** 16\
**Last updated:** [December 30, 2024, 10:05pm UTC](https://discourse.numenta.org/t/how-to-get-started-in-brain-based-ai/10757 "2024-12-30T22:05:43Z")

</div>

Background: I’m a Computer Vision Engineer working for some time in the industry now (3-4 years). HTM’s have always piqued my interest ever since I stumbled across the youtube video by Taylor. Every time I go through a …

---

## [Training HTM to learn an input-output mapping](https://discourse.numenta.org/t/training-htm-to-learn-an-input-output-mapping/11575)

<div class="topic-metadata">

**Author:** [@mindbound](https://discourse.numenta.org/u/mindbound)\
**Replies:** 3\
**Last updated:** [November 3, 2024, 8:40am UTC](https://discourse.numenta.org/t/training-htm-to-learn-an-input-output-mapping/11575 "2024-11-03T08:40:40Z")

</div>

I am trying to set up an experiment where a HTM model learns a complex mapping between an input sequence and an output sequence, for example, learning to predict the spike train of an Izhikevich neuron based on its input…

---

## [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…

---

## [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, …

---

## [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…

---

## [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,…

---

## [Question about the evolution of the neocortex](https://discourse.numenta.org/t/question-about-the-evolution-of-the-neocortex/11363)

<div class="topic-metadata">

**Author:** [@JamesLikesBrains](https://discourse.numenta.org/u/JamesLikesBrains)\
**Replies:** 2\
**Last updated:** [May 28, 2024, 11:12pm UTC](https://discourse.numenta.org/t/question-about-the-evolution-of-the-neocortex/11363 "2024-05-28T23:12:35Z")

</div>

Question that’s been bothering me. I remember in one of the Numenta videos (don’t remember which otherwise I’d post a link) Jeff mentions the neocortex didn’t evolve like the older parts of the brain, which evolved over …

---

## [How do our eyes/retina detect depth?](https://discourse.numenta.org/t/how-do-our-eyes-retina-detect-depth/11367)

<div class="topic-metadata">

**Author:** [@Hui\_Liu](https://discourse.numenta.org/u/Hui_Liu)\
**Replies:** 2\
**Last updated:** [May 25, 2024, 12:18am UTC](https://discourse.numenta.org/t/how-do-our-eyes-retina-detect-depth/11367 "2024-05-25T00:18:22Z")

</div>

Really appreciate if I could be pointed to some good summary or paper. I am curious if the depth detection is solely relies on both eyes. Or there are more details there. Thanks!!

---

## [How do HTM learn a sequence of the same input?](https://discourse.numenta.org/t/how-do-htm-learn-a-sequence-of-the-same-input/11364)

<div class="topic-metadata">

**Author:** [@Hui\_Liu](https://discourse.numenta.org/u/Hui_Liu)\
**Replies:** 1\
**Last updated:** [May 22, 2024, 7:04pm UTC](https://discourse.numenta.org/t/how-do-htm-learn-a-sequence-of-the-same-input/11364 "2024-05-22T19:04:46Z")

</div>

So suppose I have 6 mini-columns, each has 6 cells. And my input is all the same. i.e, the sequence is just AAAAAA… And because each cell can’t be in both predicted and active states, we will have to use at least two ce…

---

## [What do you know about the new ANN BitNet b1.58?](https://discourse.numenta.org/t/what-do-you-know-about-the-new-ann-bitnet-b1-58/11358)

<div class="topic-metadata">

**Author:** [@Elmarlyn\_Calderon](https://discourse.numenta.org/u/Elmarlyn_Calderon)\
**Replies:** 0\
**Last updated:** [May 12, 2024, 10:47pm UTC](https://discourse.numenta.org/t/what-do-you-know-about-the-new-ann-bitnet-b1-58/11358 "2024-05-12T22:47:11Z")

</div>

Recently Microsoft published a Paper on a new artificial neural network architecture whose weights are binary or ternary values ​​(1-bit) and I would like to know how similar it is to the binary values ​​of the weights i…

---

## [BrainX architecture](https://discourse.numenta.org/t/brainx-architecture/11269)

<div class="topic-metadata">

**Author:** [@Prakash](https://discourse.numenta.org/u/Prakash)\
**Replies:** 11\
**Last updated:** [May 8, 2024, 8:28pm UTC](https://discourse.numenta.org/t/brainx-architecture/11269 "2024-05-08T20:28:10Z")

</div>

Hi, Watch the below video and please let me know about your thoughts on this architecture in the comment section.

---

## [A question about 2017 Columns Paper](https://discourse.numenta.org/t/a-question-about-2017-columns-paper/11333)

<div class="topic-metadata">

**Author:** [@Hui\_Liu](https://discourse.numenta.org/u/Hui_Liu)\
**Replies:** 2\
**Last updated:** [May 4, 2024, 6:51pm UTC](https://discourse.numenta.org/t/a-question-about-2017-columns-paper/11333 "2024-05-04T18:51:35Z")

</div>

In the paper it mentions that During training, we reset the output layer when switching to a new object. In the brain, there are several ways the equivalent of a reset could occur..... So do we have any recent update of …

---

## [Grid Cells and the 'Where' and 'What' Pathways in the Brain?](https://discourse.numenta.org/t/grid-cells-and-the-where-and-what-pathways-in-the-brain/11329)

<div class="topic-metadata">

**Author:** [@JamesLikesBrains](https://discourse.numenta.org/u/JamesLikesBrains)\
**Replies:** 1\
**Last updated:** [April 24, 2024, 10:54pm UTC](https://discourse.numenta.org/t/grid-cells-and-the-where-and-what-pathways-in-the-brain/11329 "2024-04-24T22:54:19Z")

</div>

I recently read “Vision and Art: The Biology of Seeing” by Margaret Livingstone, and I’ve just started diving into “Conscious MIND Resonant BRAiN” by Stephen Grossberg. As I was reading, my thoughts turned to Numenta’s T…

---

## [Most frequent SDR overpowering all other bits](https://discourse.numenta.org/t/most-frequent-sdr-overpowering-all-other-bits/11242)

<div class="topic-metadata">

**Author:** [@SergeVar](https://discourse.numenta.org/u/SergeVar)\
**Replies:** 21\
**Last updated:** [April 15, 2024, 11:14pm UTC](https://discourse.numenta.org/t/most-frequent-sdr-overpowering-all-other-bits/11242 "2024-04-15T23:14:47Z")

</div>

Looking for advice. It’s been very intriguing for me to learn about the specific property of SDRs: that despite the limited amount of bits (let’s say 20 out of 4000), the number of things it can uniquely represent is gi…

---

## [How should I encode low res RGB image for OpenAI minigrid gym](https://discourse.numenta.org/t/how-should-i-encode-low-res-rgb-image-for-openai-minigrid-gym/11236)

<div class="topic-metadata">

**Author:** [@buckithed](https://discourse.numenta.org/u/buckithed)\
**Replies:** 4\
**Last updated:** [February 24, 2024, 8:11pm UTC](https://discourse.numenta.org/t/how-should-i-encode-low-res-rgb-image-for-openai-minigrid-gym/11236 "2024-02-24T20:11:47Z")

</div>

Im trying to use an htm net as part of my agent to play the minigrid gym, and am wondering if i should encode each rgb values a a scalar, or filter it into individual r g and b binary pixel representations, then feed it…

---

## [General problem solver](https://discourse.numenta.org/t/general-problem-solver/11157)

<div class="topic-metadata">

**Author:** [@Prakash](https://discourse.numenta.org/u/Prakash)\
**Replies:** 0\
**Last updated:** [December 17, 2023, 1:16pm UTC](https://discourse.numenta.org/t/general-problem-solver/11157 "2023-12-17T13:16:54Z")

</div>

There are some criterias that any network should follow in order to become a good general problem solver. Model with continuous function & plasticity property. (Continuous function - Incoming input information meeting …

---

## [Nupic/HTM for shipping target recognition](https://discourse.numenta.org/t/nupic-htm-for-shipping-target-recognition/11118)

<div class="topic-metadata">

**Author:** [@xxxxxc](https://discourse.numenta.org/u/xxxxxc)\
**Replies:** 10\
**Last updated:** [December 10, 2023, 1:58pm UTC](https://discourse.numenta.org/t/nupic-htm-for-shipping-target-recognition/11118 "2023-12-10T13:58:18Z")

</div>

If I want to use the HTM algorithm for ship target recognition and classification, what literature can I refer to and the specific approach should be? Thank you for your answer

---

## [Looking for more information regarding Numenta's L2 implementation](https://discourse.numenta.org/t/looking-for-more-information-regarding-numentas-l2-implementation/11145)

<div class="topic-metadata">

**Author:** [@Socradeez](https://discourse.numenta.org/u/Socradeez)\
**Replies:** 6\
**Last updated:** [December 8, 2023, 10:30pm UTC](https://discourse.numenta.org/t/looking-for-more-information-regarding-numentas-l2-implementation/11145 "2023-12-08T22:30:38Z")

</div>

So I’m currently working on a project to create a simplified version of the experiment laid out here: https://www.frontiersin.org/articles/10.3389/fncir.2017.00081/full You can find my current implementation here: https…

---

## [Nupic migration to python3](https://discourse.numenta.org/t/nupic-migration-to-python3/11114)

<div class="topic-metadata">

**Author:** [@prathibha](https://discourse.numenta.org/u/prathibha)\
**Replies:** 2\
**Last updated:** [November 21, 2023, 4:51am UTC](https://discourse.numenta.org/t/nupic-migration-to-python3/11114 "2023-11-21T04:51:02Z")

</div>

How can I migrate nupic from python2.7 to python3

[Next page](https://discourse.numenta.org/tag/question/20.md?match_all_tags=true&page=1&tags%5B%5D=question)