# Latest

**URL:** https://discourse.numenta.org/latest.md?no_subcategories=false&page=3

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

**Page:** 4

---

## [Concatenated ReLU](https://discourse.numenta.org/t/concatenated-relu/11950)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 3\
**Last updated:** [July 17, 2025, 12:47pm UTC](https://discourse.numenta.org/t/concatenated-relu/11950 "2025-07-17T12:47:34Z")

</div>

There is a nice discussion of the Concatenated ReLU (CReLU) activation function on page 35 of this thesis: https://scholarsarchive.byu.edu/cgi/viewcontent.cgi?article=8531&context=etd

---

## [Yoshua Bengio viewpoint on AI risks](https://discourse.numenta.org/t/yoshua-bengio-viewpoint-on-ai-risks/11951)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 0\
**Last updated:** [July 17, 2025, 3:47am UTC](https://discourse.numenta.org/t/yoshua-bengio-viewpoint-on-ai-risks/11951 "2025-07-17T03:47:49Z")

</div>

Here Yoshua Bengio talks about AI risks: https://youtu.be/g0ljOgBo5uY?si=qEtKvKWSTNDrVl2D&t=289 He didn’t get the “Condensed Matter” Nobel prize in neural networks for his work. Maybe he should chill out a bit and let …

---

## [Graph Continuous Thought Machines](https://discourse.numenta.org/t/graph-continuous-thought-machines/11892)

<div class="topic-metadata">

**Author:** [@Tofara\_Moyo](https://discourse.numenta.org/u/Tofara_Moyo)\
**Replies:** 6\
**Last updated:** [July 16, 2025, 4:22am UTC](https://discourse.numenta.org/t/graph-continuous-thought-machines/11892 "2025-07-16T04:22:58Z")

</div>

We propose a novel Graph Continuous Thought Machine (Graph CTM) architecture that integrates a simulated prefrontal cortex to enable adaptive problem-solving and decision-making. The Graph CTM leverages graph neural net-…

---

## [Continuous Thought Machine](https://discourse.numenta.org/t/continuous-thought-machine/11858)

<div class="topic-metadata">

**Author:** [@bkaz](https://discourse.numenta.org/u/bkaz)\
**Replies:** 13\
**Last updated:** [July 16, 2025, 12:00am UTC](https://discourse.numenta.org/t/continuous-thought-machine/11858 "2025-07-16T00:00:58Z")

</div>

"Therefore, in this work, we address the strong limitation imposed by overlooking neural activity as a central aspect of intelligence. We introduce the Continuous Thought Machine (CTM), a novel neural network architectur…

---

## [Can a Hebbian-like learning rule be avoiding the curse of dimensionality in sparse distributed data?](https://discourse.numenta.org/t/can-a-hebbian-like-learning-rule-be-avoiding-the-curse-of-dimensionality-in-sparse-distributed-data/11946)

<div class="topic-metadata">

**Author:** [@dmac](https://discourse.numenta.org/u/dmac)\
**Replies:** 1\
**Last updated:** [July 11, 2025, 2:49pm UTC](https://discourse.numenta.org/t/can-a-hebbian-like-learning-rule-be-avoiding-the-curse-of-dimensionality-in-sparse-distributed-data/11946 "2025-07-11T14:49:14Z")

</div>

Can a Hebbian-like learning rule be avoiding the curse of dimensionality in sparse distributed data? Maria Osório, Luis Sa-Couto & Andreas Wichert, 2024 https://doi.org/10.1007/s00422-024-00995-y Abstract It is genera…

---

## [The future is here now](https://discourse.numenta.org/t/the-future-is-here-now/11893)

<div class="topic-metadata">

**Author:** [@Bitking](https://discourse.numenta.org/u/Bitking)\
**Replies:** 10\
**Last updated:** [July 9, 2025, 11:50am UTC](https://discourse.numenta.org/t/the-future-is-here-now/11893 "2025-07-09T11:50:07Z")

</div>

Sure, LLMs are not real AI, but they accomplish a lot of what we wanted to achieve with AI, so let’s get started using them. NOTE: You don’t have to be tied to a cloud service; it is now within the grasp of any small en…

---

## [Genetic mutations are bad](https://discourse.numenta.org/t/genetic-mutations-are-bad/11926)

<div class="topic-metadata">

**Author:** [@dmac](https://discourse.numenta.org/u/dmac)\
**Replies:** 18\
**Last updated:** [July 9, 2025, 12:23am UTC](https://discourse.numenta.org/t/genetic-mutations-are-bad/11926 "2025-07-09T00:23:27Z")

</div>

While playing with evolutionary algorithms, I had the startling realization that all genetic mutations are bad. It’s common knowledge that biology abhors genetic mutation, and I assumed that was only because mutations ca…

---

## [Hypothesis: Personalities are Epigenetic](https://discourse.numenta.org/t/hypothesis-personalities-are-epigenetic/11927)

<div class="topic-metadata">

**Author:** [@dmac](https://discourse.numenta.org/u/dmac)\
**Replies:** 0\
**Last updated:** [June 28, 2025, 2:44am UTC](https://discourse.numenta.org/t/hypothesis-personalities-are-epigenetic/11927 "2025-06-28T02:44:05Z")

</div>

These two facts seem incompatible: Personalities are inherited. Identical twins separated at birth are statistically more similar than fraternal twins. The human population has almost zero genetic variation, and th…

---

## [Mini Java Collections with AI ML topics](https://discourse.numenta.org/t/mini-java-collections-with-ai-ml-topics/11896)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 1\
**Last updated:** [June 25, 2025, 1:14am UTC](https://discourse.numenta.org/t/mini-java-collections-with-ai-ml-topics/11896 "2025-06-25T01:14:53Z")

</div>

I wrote a sequence of Java source code collections on a hobby basis totally for fun and not anything else. https://archive.org/details/software?tab=collection&query=mini+java+collection&and%5B%5D=year%3A%5B2025+TO+2025%…

---

## [HTM-Based Large Language Model](https://discourse.numenta.org/t/htm-based-large-language-model/11888)

<div class="topic-metadata">

**Author:** [@MTIzNDU2Nzg5](https://discourse.numenta.org/u/MTIzNDU2Nzg5)\
**Replies:** 5\
**Last updated:** [June 25, 2025, 1:00am UTC](https://discourse.numenta.org/t/htm-based-large-language-model/11888 "2025-06-25T01:00:36Z")

</div>

Here is a somewhat working HTM based language model. It’s very small, not sure if it could handle anything more than a paragraph right now. But it works with continuous language learning. This is vibe coded with Gemin…

---

## [SwitchNet (fixed filter bank) neural network](https://discourse.numenta.org/t/switchnet-fixed-filter-bank-neural-network/11770)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 4\
**Last updated:** [June 24, 2025, 3:55am UTC](https://discourse.numenta.org/t/switchnet-fixed-filter-bank-neural-network/11770 "2025-06-24T03:55:25Z")

</div>

I tidied up the code for SwitchNet neural network and pointed out a linear mapping mathematical justification. https://sites.google.com/view/algorithmshortcuts/switchnet-newer I’m not a paid computer scientist. I don’t…

---

## [Check out my work/Blog](https://discourse.numenta.org/t/check-out-my-work-blog/11647)

<div class="topic-metadata">

**Author:** [@Prakash](https://discourse.numenta.org/u/Prakash)\
**Replies:** 0\
**Last updated:** [December 20, 2024, 3:48am UTC](https://discourse.numenta.org/t/check-out-my-work-blog/11647 "2024-12-20T03:48:00Z")

</div>

Check out my blog - I have shared my work on this blog, please have a read. Contact me if you have any queries

---

## [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…

---

## [Sharing my Pitch Detection Project](https://discourse.numenta.org/t/sharing-my-pitch-detection-project/11860)

<div class="topic-metadata">

**Author:** [@scrimix](https://discourse.numenta.org/u/scrimix)\
**Replies:** 2\
**Last updated:** [May 15, 2025, 6:04am UTC](https://discourse.numenta.org/t/sharing-my-pitch-detection-project/11860 "2025-05-15T06:04:07Z")

</div>

Hello! Today I wanted to share my project that I’ve built for my bachelors thesis (which is still in progress, but soon should be finished). It combines cochlea simulation (CARFAC) with the HTM model to re…

---

## [Random question about point neurons vs biological ones](https://discourse.numenta.org/t/random-question-about-point-neurons-vs-biological-ones/9722)

<div class="topic-metadata">

**Author:** [@JamesLikesBrains](https://discourse.numenta.org/u/JamesLikesBrains)\
**Replies:** 21\
**Last updated:** [May 23, 2025, 9:14pm UTC](https://discourse.numenta.org/t/random-question-about-point-neurons-vs-biological-ones/9722 "2025-05-23T21:14:51Z")

</div>

Question: I was watching a YouTube video and they went over the history of Neural networks. Anyway one of the early networks (I believed it had 100s of neurons in the network maybe thousands ) was able to identify photo…

---

## [New "Color" OLO and Qualias](https://discourse.numenta.org/t/new-color-olo-and-qualias/11820)

<div class="topic-metadata">

**Author:** [@roboto](https://discourse.numenta.org/u/roboto)\
**Replies:** 16\
**Last updated:** [May 20, 2025, 6:18am UTC](https://discourse.numenta.org/t/new-color-olo-and-qualias/11820 "2025-05-20T06:18:44Z")

</div>

Video explanation of OLO: https://www.youtube.com/watch?v=REozMd48QVA Theoretically speaking, if we can implant a 4th type of cone cell that can detect ultraviolet light what is the minimum required integration into the…

---

## [Dynamically generated sparsely connected network benchmark](https://discourse.numenta.org/t/dynamically-generated-sparsely-connected-network-benchmark/11864)

<div class="topic-metadata">

**Author:** [@richardbaxter](https://discourse.numenta.org/u/richardbaxter)\
**Replies:** 0\
**Last updated:** [May 16, 2025, 2:11pm UTC](https://discourse.numenta.org/t/dynamically-generated-sparsely-connected-network-benchmark/11864 "2025-05-16T14:11:11Z")

</div>

I have started to benchmark the performance of a dynamically generated sparsely connected multilayer neural network with binary weights (EISANI) on categorical datasets. Training uses no backpropagation; initialise a s…

---

## [Tuning the Neuromuscular Junction](https://discourse.numenta.org/t/tuning-the-neuromuscular-junction/11856)

<div class="topic-metadata">

**Author:** [@dmac](https://discourse.numenta.org/u/dmac)\
**Replies:** 1\
**Last updated:** [May 8, 2025, 4:37am UTC](https://discourse.numenta.org/t/tuning-the-neuromuscular-junction/11856 "2025-05-08T04:37:53Z")

</div>

In this lecture I explore how the nervous system implements closed loop control.

---

## [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.

---

## [Releasing BrainBlocks 0.7.1: Building ML Applications with HTM-Like Algorithms](https://discourse.numenta.org/t/releasing-brainblocks-0-7-1-building-ml-applications-with-htm-like-algorithms/9926)

<div class="topic-metadata">

**Author:** [@jacobeverist](https://discourse.numenta.org/u/jacobeverist)\
**Replies:** 14\
**Last updated:** [May 2, 2025, 1:29pm UTC](https://discourse.numenta.org/t/releasing-brainblocks-0-7-1-building-ml-applications-with-htm-like-algorithms/9926 "2025-05-02T13:29:18Z")

</div>

BrainBlocks 0.7.1 is released. We have previously posted about Brainblocks on this discussion board. This release includes a number of changes reflecting the user feedback provided by people here. We also included …

---

## [Programming chatGPT to make it more useful](https://discourse.numenta.org/t/programming-chatgpt-to-make-it-more-useful/11818)

<div class="topic-metadata">

**Author:** [@Bitking](https://discourse.numenta.org/u/Bitking)\
**Replies:** 2\
**Last updated:** [April 26, 2025, 9:53am UTC](https://discourse.numenta.org/t/programming-chatgpt-to-make-it-more-useful/11818 "2025-04-26T09:53:18Z")

</div>

I was working on a project to convert a ISO 9001 document to upgrade it to be ISO 17025 compliant. I found I was doing the same tasks over and over; I needed macro programming. I created this tool to make the LLM more us…

---

## [I have begun the development of a new NEAT engine](https://discourse.numenta.org/t/i-have-begun-the-development-of-a-new-neat-engine/11617)

<div class="topic-metadata">

**Author:** [@flajann2](https://discourse.numenta.org/u/flajann2)\
**Replies:** 12\
**Last updated:** [April 8, 2025, 12:04pm UTC](https://discourse.numenta.org/t/i-have-begun-the-development-of-a-new-neat-engine/11617 "2025-04-08T12:04:44Z")

</div>

I know I raised this issue years ago, about integrating HTM and NEAT (Neural Evolution of Augmenting Topologies), but at the time, I had no idea how to do that. I do now. I call it “Spiking NEAT”, and I am writing it i…

---

## [Can HTM Theories Help Improve Real-Time Anomaly Detection in Cybersecurity?](https://discourse.numenta.org/t/can-htm-theories-help-improve-real-time-anomaly-detection-in-cybersecurity/11781)

<div class="topic-metadata">

**Author:** [@derektheler](https://discourse.numenta.org/u/derektheler)\
**Replies:** 1\
**Last updated:** [March 25, 2025, 12:43pm UTC](https://discourse.numenta.org/t/can-htm-theories-help-improve-real-time-anomaly-detection-in-cybersecurity/11781 "2025-03-25T12:43:07Z")

</div>

Hello Hierarchical Temporal Memory (HTM) has been widely explored for anomaly detection in streaming data; particularly in time-series forecasting. While applications in industrial monitoring & financial fraud detection…

---

## [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 …

---

## [Dynamical constraints on neural population activity](https://discourse.numenta.org/t/dynamical-constraints-on-neural-population-activity/11765)

<div class="topic-metadata">

**Author:** [@dmac](https://discourse.numenta.org/u/dmac)\
**Replies:** 3\
**Last updated:** [March 13, 2025, 11:04am UTC](https://discourse.numenta.org/t/dynamical-constraints-on-neural-population-activity/11765 "2025-03-13T11:04:04Z")

</div>

Brain’s Hidden Learning Limits By Artem Kirsanov And here is the paper: Dynamical constraints on neural population activity Oby, E.R., Degenhart, A.D., Grigsby, E.M. et al (2025) https://doi.org/10.1038…

---

## [Three Tiers Transformers Brains](https://discourse.numenta.org/t/three-tiers-transformers-brains/11773)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 0\
**Last updated:** [March 11, 2025, 3:00am UTC](https://discourse.numenta.org/t/three-tiers-transformers-brains/11773 "2025-03-11T03:00:15Z")

</div>

Maybe this paper is interesting. https://arxiv.org/abs/2503.04848 The limitations about learning grammers might be due to artifical neural networks being heirachical associative memory, I kind of would imagine.

---

## [The geometry of addition](https://discourse.numenta.org/t/the-geometry-of-addition/11703)

<div class="topic-metadata">

**Author:** [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Replies:** 3\
**Last updated:** [March 1, 2025, 4:31am UTC](https://discourse.numenta.org/t/the-geometry-of-addition/11703 "2025-03-01T04:31:17Z")

</div>

Summing is used everywhere in machine learning, seldom though is its filtering behavior considered. https://sites.google.com/view/algorithmshortcuts/the-geometry-of-addition

---

## [Any ideas for an algorithm that learns directions?](https://discourse.numenta.org/t/any-ideas-for-an-algorithm-that-learns-directions/11745)

<div class="topic-metadata">

**Author:** [@Jossos](https://discourse.numenta.org/u/Jossos)\
**Replies:** 11\
**Last updated:** [February 21, 2025, 4:37pm UTC](https://discourse.numenta.org/t/any-ideas-for-an-algorithm-that-learns-directions/11745 "2025-02-21T16:37:46Z")

</div>

Suppose I’m taking as input an array of bits from the retina, and they each somehow know X closest distance cells. What’s an algorithm I could implement to learn directional movement? That is, one cell turns off, and ano…

---

## [Sklearn adapter for HTM?](https://discourse.numenta.org/t/sklearn-adapter-for-htm/11756)

<div class="topic-metadata">

**Author:** [@jordan.kay](https://discourse.numenta.org/u/jordan.kay)\
**Replies:** 1\
**Last updated:** [February 20, 2025, 8:56pm UTC](https://discourse.numenta.org/t/sklearn-adapter-for-htm/11756 "2025-02-20T20:56:34Z")

</div>

I’d love to use sci-kit-learn or sklearn or even just a python package to use the HTM to produce future predictions. What’s the best implementation to use?

---

## [Servos in the spinal cord](https://discourse.numenta.org/t/servos-in-the-spinal-cord/11719)

<div class="topic-metadata">

**Author:** [@dmac](https://discourse.numenta.org/u/dmac)\
**Replies:** 0\
**Last updated:** [February 8, 2025, 4:28pm UTC](https://discourse.numenta.org/t/servos-in-the-spinal-cord/11719 "2025-02-08T16:28:54Z")

</div>

In this lecture I explain how the spinal cord implements a closed loop controller for each muscle. Relevance: many members of this forum are ignorant of the spinal cord. They don’t know what the spinal co…

[Previous page](https://discourse.numenta.org/latest.md?no_subcategories=false&page=2)

[Next page](https://discourse.numenta.org/latest.md?no_subcategories=false&page=4)