# Numenta Theory **URL:** https://discourse.numenta.org/c/science/theory/5.md [Latest](https://discourse.numenta.org/latest.md) · [Categories](https://discourse.numenta.org/categories.md) · [Tags](https://discourse.numenta.org/tags.md) --- ## [About the Numenta Theory category](https://discourse.numenta.org/t/about-the-numenta-theory-category/13)
**Author:** [@rhyolight](https://discourse.numenta.org/u/rhyolight)\ **Replies:** 0\ **Last updated:** [March 10, 2016, 4:02pm UTC](https://discourse.numenta.org/t/about-the-numenta-theory-category/13 "2016-03-10T16:02:40Z")
Discussions about Numenta’s HTM theory, not software implementations of the theory. Posting Guidelines This is a list for discussing theoretical aspects of HTM theory. It is not a list for general discussions of AI and… --- ## [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)
**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")
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… --- ## [Thousand brains recent paper](https://discourse.numenta.org/t/thousand-brains-recent-paper/11688)
**Author:** [@cezar\_t](https://discourse.numenta.org/u/cezar_t)\ **Replies:** 2\ **Last updated:** [January 9, 2025, 2:54pm UTC](https://discourse.numenta.org/t/thousand-brains-recent-paper/11688 "2025-01-09T14:54:18Z")
I think it wasn’t mentioned yet \[2412.18354v1\] The Thousand Brains Project: A New Paradigm for Sensorimotor Intelligence --- ## [Resolving ambiguity / uncertainty](https://discourse.numenta.org/t/resolving-ambiguity-uncertainty/11616)
**Author:** [@Mark\_Springer](https://discourse.numenta.org/u/Mark_Springer)\ **Replies:** 1\ **Last updated:** [November 19, 2024, 12:17pm UTC](https://discourse.numenta.org/t/resolving-ambiguity-uncertainty/11616 "2024-11-19T12:17:15Z")
I was reading about the proposed SDK, and I was wondering, how does uncertainty drive exploration? For instance, suppose you are blindfolded and feeling the contours of an object with your finger. You are uncertain wha… --- ## [Paper on combining "cortical" WTA with transformers](https://discourse.numenta.org/t/paper-on-combining-cortical-wta-with-transformers/11562)
**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")
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… --- ## [Missing cortical column concept in some papers](https://discourse.numenta.org/t/missing-cortical-column-concept-in-some-papers/11509)
**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")
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 thousand brains with concept space structured by a circle of fifths grid completion of TBT](https://discourse.numenta.org/t/a-thousand-brains-with-concept-space-structured-by-a-circle-of-fifths-grid-completion-of-tbt/11235)
**Author:** [@Tofara\_Moyo](https://discourse.numenta.org/u/Tofara_Moyo)\ **Replies:** 2\ **Last updated:** [February 22, 2024, 4:30pm UTC](https://discourse.numenta.org/t/a-thousand-brains-with-concept-space-structured-by-a-circle-of-fifths-grid-completion-of-tbt/11235 "2024-02-22T16:30:07Z")
Structuring Concept Space With The Musical Circle Of Fifths By Utilizing Music Grammar Based Activations-Tofara Moyo Abstract In this paper, we explore the intriguing similarities between the structure of a discrete neu… --- ## [The "delta" problem!](https://discourse.numenta.org/t/the-delta-problem/1587)
**Author:** [@mraptor](https://discourse.numenta.org/u/mraptor)\ **Replies:** 6\ **Last updated:** [February 9, 2024, 1:11pm UTC](https://discourse.numenta.org/t/the-delta-problem/1587 "2024-02-09T13:11:37Z")
I had for sometime been thinking of the "delta"-problem ( this is how I dubbed it, dont know if it is a known problem in ML). It is easier to illustrate it with example. Let say we have the following sequence : 10, 15,… --- ## [TM escalation by failure prediction](https://discourse.numenta.org/t/tm-escalation-by-failure-prediction/11168)
**Author:** [@cezar\_t](https://discourse.numenta.org/u/cezar_t)\ **Replies:** 2\ **Last updated:** [January 8, 2024, 5:19am UTC](https://discourse.numenta.org/t/tm-escalation-by-failure-prediction/11168 "2024-01-08T05:19:14Z")
Hi, Here-s a proposal about how to stack several TM blocks at different time frames, in a manner similar to STREAMER (recently mentioned here) and Ogma’s SPH as a means to: deal with limited learning capacity of any… --- ## ["⊤" Terminology used in "Avoiding Catastrophe" and "Going Beyond the Point Neuron" papers](https://discourse.numenta.org/t/terminology-used-in-avoiding-catastrophe-and-going-beyond-the-point-neuron-papers/11010)
**Author:** [@michaelroyames](https://discourse.numenta.org/u/michaelroyames)\ **Replies:** 6\ **Last updated:** [October 11, 2023, 1:07am UTC](https://discourse.numenta.org/t/terminology-used-in-avoiding-catastrophe-and-going-beyond-the-point-neuron-papers/11010 "2023-10-11T01:07:00Z")
Please explain how to interpret or understand the “⊤” notation used within equations in some of Numenta’s research papers. That’s a symbol that looks like “T” - a capital t. For example: In “Avoiding Catastrophe: Activ… --- ## [Molyneux's Question--good fit for an HTM answer](https://discourse.numenta.org/t/molyneuxs-question-good-fit-for-an-htm-answer/10984)
**Author:** [@EEProf](https://discourse.numenta.org/u/EEProf)\ **Replies:** 5\ **Last updated:** [September 26, 2023, 8:10am UTC](https://discourse.numenta.org/t/molyneuxs-question-good-fit-for-an-htm-answer/10984 "2023-09-26T08:10:03Z")
I was not aware of this ‘question’ until I saw this call for abstracts. Looks a bit like the finger knowing the cup handle or the eyelid feeling the shape of the contact lens… --- ## [Please give me research topic on HTM](https://discourse.numenta.org/t/please-give-me-research-topic-on-htm/10989)
**Author:** [@Cirno\_09](https://discourse.numenta.org/u/Cirno_09)\ **Replies:** 2\ **Last updated:** [September 21, 2023, 6:17pm UTC](https://discourse.numenta.org/t/please-give-me-research-topic-on-htm/10989 "2023-09-21T18:17:42Z")
Hello. I am a college student and I have read On Intelligence by Jeff Hawkins and am very impressed and would like to do research on HTM, but I am not sure of a specific research topic using HTM algorithms. Are there any… --- ## [In the context of HTM how does the prefrontal cortex, and thus it’s associated functions, work?](https://discourse.numenta.org/t/in-the-context-of-htm-how-does-the-prefrontal-cortex-and-thus-it-s-associated-functions-work/10893)
**Author:** [@Prometheushunter2](https://discourse.numenta.org/u/Prometheushunter2)\ **Replies:** 1\ **Last updated:** [July 31, 2023, 11:51pm UTC](https://discourse.numenta.org/t/in-the-context-of-htm-how-does-the-prefrontal-cortex-and-thus-it-s-associated-functions-work/10893 "2023-07-31T23:51:48Z")
I know the basics of HTM and how it functions, but can’t figure out how something like that would work to create things like working memory and planning. Not saying it can’t, just that can’t figure out how it would be wi… --- ## [Growing Temporal Memory (GTM)](https://discourse.numenta.org/t/growing-temporal-memory-gtm/10857)
**Author:** [@cezar\_t](https://discourse.numenta.org/u/cezar_t)\ **Replies:** 15\ **Last updated:** [July 7, 2023, 6:54pm UTC](https://discourse.numenta.org/t/growing-temporal-memory-gtm/10857 "2023-07-07T18:54:26Z")
TLDR Here I propose a TM block which instead of having a fixed depth (column size) it starts with all columns shallow and each column grows (stacks new cells) as necessary, how TM learning rules could be changed in ord… --- ## [Does HTM create an internal model?](https://discourse.numenta.org/t/does-htm-create-an-internal-model/10836)
**Author:** [@Mark\_Springer](https://discourse.numenta.org/u/Mark_Springer)\ **Replies:** 6\ **Last updated:** [July 4, 2023, 2:13am UTC](https://discourse.numenta.org/t/does-htm-create-an-internal-model/10836 "2023-07-04T02:13:46Z")
I was reading recently Steven Wolfram’s remarks on his website about ChatGPT, where he says it is discovering semantic rules and that language may follow rules of meaning that we didn’t know about. As far as I understa… --- ## [New Learning Rule for HTM Synapses](https://discourse.numenta.org/t/new-learning-rule-for-htm-synapses/10816)
**Author:** [@dmac](https://discourse.numenta.org/u/dmac)\ **Replies:** 17\ **Last updated:** [June 30, 2023, 1:45am UTC](https://discourse.numenta.org/t/new-learning-rule-for-htm-synapses/10816 "2023-06-30T01:45:51Z")
The Old Model To refresh your memory: HTM synapses learn with following rules: if dendritic\_segment\_is\_active: if axon\_is\_active: permanence += increment // Potentiate the synapse else: perman… --- ## [Nano Particles that can turn a wet-lab into a dry in-vivo lab. Numenta should partner with these labs](https://discourse.numenta.org/t/nano-particles-that-can-turn-a-wet-lab-into-a-dry-in-vivo-lab-numenta-should-partner-with-these-labs/10598)
**Author:** [@BrainConstellation](https://discourse.numenta.org/u/BrainConstellation)\ **Replies:** 4\ **Last updated:** [March 28, 2023, 10:52pm UTC](https://discourse.numenta.org/t/nano-particles-that-can-turn-a-wet-lab-into-a-dry-in-vivo-lab-numenta-should-partner-with-these-labs/10598 "2023-03-28T22:52:39Z")
Since I have common roots with Rafa Yuste, being a Spanish-American raised in Madrid with the same passion for Neuroscience, I always follow his phenomenal research. He is a Professor at Columbia and one of the Initiato… --- ## [Layer abbreviations and layer diagrams](https://discourse.numenta.org/t/layer-abbreviations-and-layer-diagrams/10545)
**Author:** [@Markus](https://discourse.numenta.org/u/Markus)\ **Replies:** 2\ **Last updated:** [March 21, 2023, 1:29am UTC](https://discourse.numenta.org/t/layer-abbreviations-and-layer-diagrams/10545 "2023-03-21T01:29:42Z")
In the Voting Part One video (see link) there was a diagram that contained various abbreviations that i can’t assign/associate. Does anyone know more about this? (tt, cc, cc-ns, ip, mp, bp) Is there a cu… --- ## [How to know the individuals SDRs in a union of SDRs in the output of a TM?](https://discourse.numenta.org/t/how-to-know-the-individuals-sdrs-in-a-union-of-sdrs-in-the-output-of-a-tm/10537)
**Author:** [@educob](https://discourse.numenta.org/u/educob)\ **Replies:** 2\ **Last updated:** [March 9, 2023, 11:02am UTC](https://discourse.numenta.org/t/how-to-know-the-individuals-sdrs-in-a-union-of-sdrs-in-the-output-of-a-tm/10537 "2023-03-09T11:02:37Z")
Let’s say an TM layer receives some inputs (like a chord sequence) and the output is the union of the possible chords that follow the input sequence. Is there a way to know the indificual chords that fomr the union by l… --- ## [Extrapolating and interpolating quantities with HTM](https://discourse.numenta.org/t/extrapolating-and-interpolating-quantities-with-htm/10468)
**Author:** [@seanjhardy](https://discourse.numenta.org/u/seanjhardy)\ **Replies:** 13\ **Last updated:** [February 15, 2023, 6:20pm UTC](https://discourse.numenta.org/t/extrapolating-and-interpolating-quantities-with-htm/10468 "2023-02-15T18:20:34Z")
The human brain doesn’t need to build individual interpretations of all the numbers we encounter in daily life. We can utilise our understanding of numbers across domains, 1 million dollars, 5 hours, 500m etc. and also l… --- ## [Building up longer term contextual representations with HTM](https://discourse.numenta.org/t/building-up-longer-term-contextual-representations-with-htm/10469)
**Author:** [@seanjhardy](https://discourse.numenta.org/u/seanjhardy)\ **Replies:** 9\ **Last updated:** [February 2, 2023, 7:33pm UTC](https://discourse.numenta.org/t/building-up-longer-term-contextual-representations-with-htm/10469 "2023-02-02T19:33:36Z")
Li et al. writes “higher levels of cortical organisation increasingly integrate information over longer timescales, similar to how higher layers in the visual cortex correspond to larger spatial patterns.” (https://www.p… --- ## [Is input prediction the actual purpose of a column?](https://discourse.numenta.org/t/is-input-prediction-the-actual-purpose-of-a-column/10451)
**Author:** [@cezar\_t](https://discourse.numenta.org/u/cezar_t)\ **Replies:** 14\ **Last updated:** [January 31, 2023, 10:50pm UTC](https://discourse.numenta.org/t/is-input-prediction-the-actual-purpose-of-a-column/10451 "2023-01-31T22:50:14Z")
A TM at time t is simply trained to predict its input at time t+1. From ML perspective, this is very restrictive. Let’s take reinforcement learning (RL). Which, if someone aims to replicate biology should not ignore. … --- ## [Rapid Learning](https://discourse.numenta.org/t/rapid-learning/10440)
**Author:** [@ediril](https://discourse.numenta.org/u/ediril)\ **Replies:** 13\ **Last updated:** [January 31, 2023, 6:00pm UTC](https://discourse.numenta.org/t/rapid-learning/10440 "2023-01-31T18:00:15Z")
Humans take years to learn certain skills as babies/kids but once a certain level of maturity is reached, it doesn’t always take a long time to learn new things. It might take a single showing, maybe two… of course some … --- ## [Object modeling pre- and post- 9/21 Hawkins talks](https://discourse.numenta.org/t/object-modeling-pre-and-post-9-21-hawkins-talks/9579)
**Author:** [@jes](https://discourse.numenta.org/u/jes)\ **Replies:** 3\ **Last updated:** [December 29, 2022, 10:02am UTC](https://discourse.numenta.org/t/object-modeling-pre-and-post-9-21-hawkins-talks/9579 "2022-12-29T10:02:24Z")
In September, Jeff gave two talks and led a discussion on object modeling. In my view these talks are of very great significance. Yet, on this forum I can find no discussion of the important points made in these talks (u… --- ## [Share an experiment on the role of the thalamus on the optic neural circuit](https://discourse.numenta.org/t/share-an-experiment-on-the-role-of-the-thalamus-on-the-optic-neural-circuit/10211)
**Author:** [@Z\_boy2017](https://discourse.numenta.org/u/Z_boy2017)\ **Replies:** 0\ **Last updated:** [October 22, 2022, 9:26am UTC](https://discourse.numenta.org/t/share-an-experiment-on-the-role-of-the-thalamus-on-the-optic-neural-circuit/10211 "2022-10-22T09:26:13Z")
Hi everyone, I’m an HTM theory lover, sharing an interesting experiment, The method of 3D stereoscopic painting is associated with the exploration of consciousness or the scanning pattern of attention in the eyes by ove… --- ## [Sources for HTM minicolumn bursting phenomenon?](https://discourse.numenta.org/t/sources-for-htm-minicolumn-bursting-phenomenon/10148)
**Author:** [@altshiftj](https://discourse.numenta.org/u/altshiftj)\ **Replies:** 7\ **Last updated:** [October 2, 2022, 1:19am UTC](https://discourse.numenta.org/t/sources-for-htm-minicolumn-bursting-phenomenon/10148 "2022-10-02T01:19:52Z")
Hey everybody. Is there a specific source or set of sources for the bursting phenomenon implemented in the HTM algorithm? I was wondering if the phenomenon has been observed in the neocortex, or if it is just a feature… --- ## [An HTM compatible theory of attention](https://discourse.numenta.org/t/an-htm-compatible-theory-of-attention/9640)
**Author:** [@Panaman](https://discourse.numenta.org/u/Panaman)\ **Replies:** 13\ **Last updated:** [September 5, 2022, 10:02pm UTC](https://discourse.numenta.org/t/an-htm-compatible-theory-of-attention/9640 "2022-09-05T22:02:13Z")
I’ve been working hard to grok HTM theory. If I’m understanding correctly, the mechanism behind “attention” would best be explained by SDRs inhibiting more parts of the brain as they are recruited to model something inte… --- ## [Reference frames and my thalamus, \[introspection warning\]](https://discourse.numenta.org/t/reference-frames-and-my-thalamus-introspection-warning/9941)
**Author:** [@JarvisGoBrr](https://discourse.numenta.org/u/JarvisGoBrr)\ **Replies:** 7\ **Last updated:** [August 10, 2022, 3:05pm UTC](https://discourse.numenta.org/t/reference-frames-and-my-thalamus-introspection-warning/9941 "2022-08-10T15:05:41Z")
I’ll just leave this here, This is all a result from introspection from a single individual so take this post and everything I say here with a very big grain of salt. So, I suffer from visual snow and I have always obse… --- ## [Scaled dot product attention mechanism in cortical columns?](https://discourse.numenta.org/t/scaled-dot-product-attention-mechanism-in-cortical-columns/9913)
**Author:** [@Jim](https://discourse.numenta.org/u/Jim)\ **Replies:** 15\ **Last updated:** [July 15, 2022, 12:48am UTC](https://discourse.numenta.org/t/scaled-dot-product-attention-mechanism-in-cortical-columns/9913 "2022-07-15T00:48:33Z")
Hi, I’m wondering if there is any evidence of something similar to a scalar product attention mechanism in the cortical column or in Numenta’s proposed architecture for intelligent machines? Thanks for any pointers here… --- ## [Synaptic mess in my understanding of permanences](https://discourse.numenta.org/t/synaptic-mess-in-my-understanding-of-permanences/9871)
**Author:** [@cezar\_t](https://discourse.numenta.org/u/cezar_t)\ **Replies:** 4\ **Last updated:** [July 9, 2022, 11:36am UTC](https://discourse.numenta.org/t/synaptic-mess-in-my-understanding-of-permanences/9871 "2022-07-09T11:36:02Z")
It seems I can’t get clear view upon both HTM algorithms and neurological perspective, and I think the following problem is fogging me. Assume there one synapse S and two neurons A is presynaptic and B postsynaptic. It… [Next page](https://discourse.numenta.org/c/science/theory/5.md?page=1)