# Intelligence is embarrassingly simple

**URL:** <https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930>\
**Category:** General Neuroscience\
**Created:** [August 11, 2023, 10:03pm UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930 "2023-08-11T22:03:46Z")\
**Posts on this page:** 20\
**Page:** 1

<div class="post-metadata">

**Author:** ![Bullbash](https://avatars.discourse-cdn.com/v4/letter/b/e68b1a/32.png) [@Bullbash](https://discourse.numenta.org/u/Bullbash)\
**Post date:** [August 11, 2023, 10:03pm UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/1 "2023-08-11T22:03:46Z")

</div>

Gentlemen (and Ladies),  
I’m not gonna flabbergast you here, this is my last message - I promise.

Imagine a flexible LED matrix - like in a TV - but elastic. Instead of diodes  
it is made of neurons. Lets say the left side is where input sensors are.  
The next rows to right is where activations go. Those neurons’ rows dedicate  
a new node for every new patterns it observes. Like “abc” input produces  
2^3 patterns. Sounds awfully many? it does - it expands as C(N, M), faster then exponential.

But do not fear :-), after a few rows it stops growing and starts shrinking, just  
like C(N, M) suggests. N is a sensor(s) size, M is the size of a combination.  
The LED matrix takes a diamond shape with simple [multimodal] patterns in the West and  
complex patterns in the East.

Human Language defines around a few thousand labeled Eastern patterns - that’s  
the size of a diamond approximation.

That describes “unsupervised” patterns learning. Just collect frequencies.

Obviously, growing the “LED” matrix is continual [Hebbian] process -  
get new input - create new nodes. Get recurrent input - increase synaptic  
strength.

Now, each pattern represented by a neuron could be associated with classes  
(or rewards) relations, think additional specific synapses.

By design, every next input modifies the Network and does inference as well,  
by using “associated” synapses.

That is an insect level. The Net gets input - it responds.

By design, dedicated nodes (a node a pattern) could message laterally  
(sideways), thus generating new combinations of nodes (patterns) and  
producing new, more complex, combinations (meaning thinking without input).

And I must tell you - irresponsible thinking can produce pretty stupid  
and dangerous new ideas-combinations.

By design, dedicated nodes (a node a pattern) can message back to  
“predict, inject context, hypnotize”, which undedicated nodes  
can not.

That is pretty much it.

There are a few logistics problems:  
how to grow that Net, how to contain growth, how to assign and use associations,  
how to grow motor Net.

Those are solvable. I’ve done it, so can you. Best!

---

<div class="post-metadata">

**Author:** ![Bitking](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/bitking/32/3099_2.png) [@Bitking](https://discourse.numenta.org/u/Bitking)\
**Post date:** [August 12, 2023, 5:12pm UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/2 "2023-08-12T17:12:55Z")

</div>

Naturally, a working example would go a long way to demonstrating how well this works.  
Perhaps in a robot?

---

<div class="post-metadata">

**Author:** ![Bullbash](https://avatars.discourse-cdn.com/v4/letter/b/e68b1a/32.png) [@Bullbash](https://discourse.numenta.org/u/Bullbash)\
**Post date:** [August 12, 2023, 7:34pm UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/4 "2023-08-12T19:34:37Z")

</div>

No robots - cannot afford it. Text/images are nice proving grounds. Here are working examples:  
[https://youtu.be/\_NjjKeGltBw](https://youtu.be/_NjjKeGltBw) (Sep 2020, breakthrough with finding a distance measure working in feature spaces ~10^6 dimensionality)  
[IMDB Reviews Dataset - YouTube](https://youtu.be/-JrWz1MONYE) (same thing - IMDB)  
[https://youtu.be/CJY0zgMBwb0](https://youtu.be/CJY0zgMBwb0) (Amazon sentiment)

Fresh repo (used it as backup, kind of messy, but working: classification, generation):

> **[GitHub - MasterAlgo/GPT-Teaser](https://github.com/MasterAlgo/GPT-Teaser)**
>
> Contribute to MasterAlgo/GPT-Teaser development by creating an account on GitHub.

Last repo (backup again, the simplest implementation: local continual Hebbian learning, no BP, single [dah epoch, structurally and synaptically plastic, emulating spiking messaging). Does online clustering of tokens streams (characters, words, tokens, integers). Want to play - start the jar, tune config file: number of streams +++.

> **[GitHub - MasterAlgo/Simply-Spiking](https://github.com/MasterAlgo/Simply-Spiking)**
>
> Contribute to MasterAlgo/Simply-Spiking development by creating an account on GitHub.

Here is video of how it works : [Sign Up | LinkedIn](https://www.linkedin.com/feed/update/urn:li:activity:7082368680084262912)

Here is video of how structural (LED) matrix is built:

> **[Alex Semenov on LinkedIn: Myths of the Instance Based Learning](https://www.linkedin.com/posts/activity-7067534016710656000-tO6L)**
>
> Myths of the Instance Based Learning

Here are examples of generations (nano generator ~200 lines of Java, on top of trained “language model” - stochastic parrot:

> **[Alex Semenov on LinkedIn: GPTs are doing generation the hard way. I put...](https://www.linkedin.com/posts/activity-7042481252767068160-986K)**
>
> GPTs are doing generation the hard way. I put together 200 lines to collect n-grams (character and word levels) and 200 more to use collection for actual…

“Never again she be able to get a better look at the man who had been in the same way as the malfunctioning one.”(c)

> **[Alex Semenov on LinkedIn: First generation attempt... my framework, 45...](https://www.linkedin.com/posts/activity-6862516771040174080-vsC1)**
>
> First generation attempt... my framework, 45 minutes of training on CPU only PC, 1 minute of generation... 1 BLN parameters. 100 lines of actual generation…

“I suspect real gangbangers do not wear T-shirts outside on new years eve in northern Europe.”(c)

> **[Alex Semenov on LinkedIn: Second attempt of content generation: now trained...](https://www.linkedin.com/posts/activity-6862836553484500992-iyEF)**
>
> Second attempt of content generation: now trained on 8GB RAM PC on IMDB dataset. The model comprised of ~450K parameters and generates a bit dumbier content…

Some musing on how lateral messaging between dedicated neurons could work:

> **[Alex Semenov on LinkedIn: Side Propagation](https://www.linkedin.com/posts/activity-6950148118248124418-KpE9)**
>
> Side Propagation

(side propagation 🙂 )

And if you not tired yet, here is an attempt (#17) to describe what’s going on and how it works:

> **[LinkedIn: Log In or Sign Up](https://www.linkedin.com/pulse/draft/AgEJA9fvFUdb_wAAAYnrOzf-rOWwCWyd3seVplZN8C4jfRnnUo1nVXmCgEUzkRT5nDYl3Ic)**
>
> 750 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.

Enjoy.

Images are not that obvious - have no publishable posts about. But - have no reason to mislead - it works (trains, classifies, generalizes) on the same platform.

I’m leaving tomorrow morning for a week - so, do not miss me much, be back - will respond 🙂

---

<div class="post-metadata">

**Author:** ![Bullbash](https://avatars.discourse-cdn.com/v4/letter/b/e68b1a/32.png) [@Bullbash](https://discourse.numenta.org/u/Bullbash)\
**Post date:** [August 12, 2023, 7:38pm UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/5 "2023-08-12T19:38:38Z")

</div>

> [@Casey](#):
>
> Why argue that intelligence should be built like LLMs?

That is out of context. I never said intelligence is LLM-like. I said that language might reside at the top layers (Eastern) of the structurally plastic net. Got to go, later.

---

<div class="post-metadata">

**Author:** ![Casey](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/casey/32/2874_2.png) [@Casey](https://discourse.numenta.org/u/Casey)\
**Post date:** [August 13, 2023, 1:59am UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/6 "2023-08-13T01:59:00Z")

</div>

Right, sorry. I should’ve read more carefully.

I still think this applies:

> how do you take an object which you’re never seen before and mentally rotate it? Something to do with the more abstract patterns, but just taking patterns of patterns won’t get you there, because there’s a temporal aspect there, or at least something more.

Have a good trip.

---

<div class="post-metadata">

**Author:** ![neel\_g](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/neel_g/32/5503_2.png) [@neel\_g](https://discourse.numenta.org/u/neel_g)\
**Post date:** [August 13, 2023, 1:59am UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/7 "2023-08-13T01:59:49Z")

</div>

interesting work, but the performance seems pretty lacking - 83% isn’t a good score, especially with 1 BLN (Billion?) parameters - rule based systems can trivially outperform that…

---

<div class="post-metadata">

**Author:** ![Bullbash](https://avatars.discourse-cdn.com/v4/letter/b/e68b1a/32.png) [@Bullbash](https://discourse.numenta.org/u/Bullbash)\
**Post date:** [August 13, 2023, 2:41am UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/8 "2023-08-13T02:41:16Z")

</div>

Thank you for “interesting work”. It was 87% accuracy of IMDB sentiment, plus ~40% of fine grained sentiment - 8 classes when continually learning. 87% comparable to “vowpal wabbit” trained continually, but there are a few advantages. Achieved on first 10% of samples, trained on IMDB, recognized Amazon sentiment. Same engine processes images - by converting to a sequence of BLOBs. It’s a big talk, got to go. BTW - 1BLN (Billion, correct) - parameters (synapses) generated in a hour on a 128GB RAM PC. Max I did 18BLN by dumping to disk and then merging. Was pissed of by OpenAI(?) bragging about a couple of BLN parameters trained… think of knowledge transfer 🙂 (merging RAM and disk).  
Anyways, have a good week everybody. Cheers!

---

<div class="post-metadata">

**Author:** ![Prakash](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/prakash/32/6117_2.png) [@Prakash](https://discourse.numenta.org/u/Prakash)\
**Post date:** [August 13, 2023, 3:54am UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/9 "2023-08-13T03:54:56Z")

</div>

![Untitled18_20230714225630](https://canada1.discourse-cdn.com/flex030/uploads/numenta/original/2X/a/aacab7667b1163db0c2fade8a73aaf45359b452d.png)

I would like to pose a question why the net has to grow to the new inputs.  
Lets say we have 10 hours of active input getting into our brain, and the next 1 hour input too gets inside the brain? Why?

---

<div class="post-metadata">

**Author:** ![SeanOConnor](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/seanoconnor/32/3441_2.png) [@SeanOConnor](https://discourse.numenta.org/u/SeanOConnor)\
**Post date:** [August 14, 2023, 2:26am UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/10 "2023-08-14T02:26:36Z")

</div>

If except if trees can generate viable sentences with correct spelling using almost no computational resources. You just simple scan through the data once or twice and update some entries in a hash table. The context length is only a few characters though.  
I see what you mean that there are potentially simpler LLMs that could beat neural network LLMs. Given that less compute should be required let the person who can imagine such a construct implement it and show proof.

Though I have to agree that showing proof by theory and implementation, by someone outside the social hierarchies involved can simply not be enough.  
But then the last laugh is on the higher ups.

I was just thinking about how to explain one aspect of neural networks which is how a composition of weighted sums of weighted sums of … differs from a simple weighted sum. Since the composition is reducible to a simple weighted sum by basic linear algebra. And the difference is that during the simplification of a composition of weighted sums each weight is the result of multiple terms multiplied together. And that means there is exponentiation going. Some of the weights will decay down to zero and others will inflate.  
If the weights in each weighted sum in a composition of weighted sums are from the the uniform random distribution, that isn’t going to be the case after simplification.

---

<div class="post-metadata">

**Author:** ![cezar\_t](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/cezar_t/32/4451_2.png) [@cezar\_t](https://discourse.numenta.org/u/cezar_t)\
**Post date:** [August 14, 2023, 10:51am UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/11 "2023-08-14T10:51:00Z")

</div>

This is very interesting, I also think growing a connectome on new data instead of training an arbitrary large network has several advantages.

Instead (or before) published papers maybe some intermediate description of key concepts might attract interest from people willing to explore it

---

<div class="post-metadata">

**Author:** ![cezar\_t](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/cezar_t/32/4451_2.png) [@cezar\_t](https://discourse.numenta.org/u/cezar_t)\
**Post date:** [August 14, 2023, 11:53am UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/12 "2023-08-14T11:53:59Z")

</div>

> [@Bullbash](#):
>
> No robots - cannot afford it

There are robot environments with various degrees of complexity on openai’s gym. I am not sure whether there are any Java equivalents or APIs on top of it

---

<div class="post-metadata">

**Author:** ![Bullbash](https://avatars.discourse-cdn.com/v4/letter/b/e68b1a/32.png) [@Bullbash](https://discourse.numenta.org/u/Bullbash)\
**Post date:** [August 17, 2023, 2:47am UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/13 "2023-08-17T02:47:20Z")

</div>

There are a couple of people saying I cannot explain what I know. Lets see.  
Let me know what point is difficult to understand.

a) conventional neuron model suggests a neuron has  
a set of pre-synaptic (input) weighted links (addresses, pointers, IDs),  
with real number inputs,  
a set of postsynaptic links and an activation function broadcasting a  
real number output.

I suggest that a neuron has two sets of pre-synaptic inputs:  
a structural one of “binary” links, activating the neuron only  
if all the inputs are “ones”. That set answers questions “what”, " where" and “when”.  
The second set is conventional analogous inputs reflecting value of  
the neuron to the owner. Activation is conventional linear combination,  
but activated only if “structural” inputs are al “ones” (logical AND).

b) The neural net organized in several layers with initially disconnected nodes.  
Input creates connections. Like “abcd” create “ab” and “cd” on the first layer,  
“ab” + “cd” = “abcd” - the only second layer node uniting “ab” and “cd”.

The bigger the sensor the more nodes it generates.

c) Here we must remember that two major ML watersheds are Model Based and  
Instance Based approaches (Google). Point b) extends and exacerbates  
problems of IBL - but solves many more.  
Instead of memorizing “instances” the Net memorizes all the “sub-instances”  
of instances. It requires more memory (RAM), but solves comparison of  
instances of different length [irregularly sampled],  
allows to explicitly calculate Kolmogorov complexity  
(as function of set of sub-instances of different sizes),  
solves continual learning and knowledge transfer, employs local learning,  
and allows associate a node with either unassociated frequency [unsupervised],  
frequency associated with a particular [multiple] classes [supervised] and  
frequency associated with complex [delayed] [multiple] rewards - reinforced learning.

d) The incarnated IBL seems impossible because of a number of potential  
nodes/connections to form the “structural” net. Experiments show that  
exponential growth could be contained by removing irrelevant nodes and  
with help of natural recurrence of patterns.

e) Inference made by activation of sparse number of “structural” nodes,  
accumulating analogous “attitudal” connections, makes stochastic inference  
explainable. One knows “who/what” and “how strong” voters are. Tested in experiments.

f) Unlike Model Based Learning, IBL enables meaningful messaging between “structural”  
nodes. Because every node bears a particular pattern. At the top layers a node  
bears a complex idea/concept. Now communication between nodes enables create new  
connections without sensory input. Backward connections support “context injection”  
up to hypnosis, sideways messaging implement “thinking”.  
IBL bridges stochastic inference with symbolic one - no MBL will ever do it.  
By design.

g) All that messaging could be implemented as spiking protocol. Because spikes  
both can convey as both “binary” (barcodes) and analogous (integratable) info.  
That is the essence of the “neural code”.

h) Simple IBL containers could be implemented as a short program on von Neumann  
conventional PC with time complexity as O(nodes number). HW platforms like Intel  
Loihi will learn and infer with time complexity as O(layers number).

In one sitting we are here solving “neural code”, Kolmogorov complexity,  
local continual training, dismissing principal differences between UL, SL and RL,  
explainable inference, bridging stochastic to symbolic.

Many experiments/sources are listed above. What is not clear, I wonder?  
I’ll keep my peace now.

---

<div class="post-metadata">

**Author:** ![Bitking](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/bitking/32/3099_2.png) [@Bitking](https://discourse.numenta.org/u/Bitking)\
**Post date:** [August 17, 2023, 4:04am UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/14 "2023-08-17T04:04:27Z")

</div>

This misses much of the known behaviors of cells.  
It’s late and I need to go to bed but I will just say that you miss known temporal behavior and some known spatial processing.  
It may work like a fancy perception and that is sufficient for many things, but I expect my neural models to do more.

---

<div class="post-metadata">

**Author:** ![cezar\_t](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/cezar_t/32/4451_2.png) [@cezar\_t](https://discourse.numenta.org/u/cezar_t)\
**Post date:** [August 17, 2023, 8:58am UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/15 "2023-08-17T08:58:59Z")

</div>

Pardon my mind’s slowness, one of the things I find hard to understand is, the following, especially the highlighted part:

> [@Bullbash](#):
>
> I suggest that a neuron has two sets of pre-synaptic inputs:  
> a structural one of “binary” links, activating the neuron only  
> if all the inputs are “ones”. That set answers questions “what”, " where" and “when”.  
> The second set is conventional analogous inputs reflecting **value of**  
> **the neuron to the owner.** Activation is conventional linear combination,  
> but activated only if “structural” inputs are al “ones” (logical AND).

- What/who is an neuron’s _owner_?
- from following paragraph, seems more like a threshold value meant to activate the whole neuron - much like a node’s bias value, but bias (like weights) is just another trainable parameter, not an input. Or in your case, you simply describe it as an AND function over binary inputs, which again, is neither _analogue_ nor _input_

PS it can be read as the analogue input is like an attention bias, so it allows the mysterious “owner” to look for/highlight specific input patterns. This could be powerful - a substrate to implement _attention_ - yet opens a pandora’s box of questions about who, and by what logic, is controlling the attention patterns.

---

<div class="post-metadata">

**Author:** ![cezar\_t](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/cezar_t/32/4451_2.png) [@cezar\_t](https://discourse.numenta.org/u/cezar_t)\
**Post date:** [August 17, 2023, 9:54am UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/16 "2023-08-17T09:54:13Z")

</div>

> [@Bitking](#):
>
> I will just say that you miss known temporal behavior and some known spatial processing.

well, if it works, it could be a base on top of which to implement either/both. As in transformers, a certain structuring/encoding of input(s) allows them to process both spatial (images) and sequential (text) data, on top of and without having to change the fundamentals of matrix dot product.

---

<div class="post-metadata">

**Author:** ![Bullbash](https://avatars.discourse-cdn.com/v4/letter/b/e68b1a/32.png) [@Bullbash](https://discourse.numenta.org/u/Bullbash)\
**Post date:** [August 17, 2023, 1:23pm UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/17 "2023-08-17T13:23:32Z")

</div>

> [@cezar\_t](#):
>
> What/who is an neuron’s _owner_?

I was convinced the neuron’s owner is the brain owner (intellectual entity?), which tend to adapt and survive.

> [@cezar\_t](#):
>
> seems more like a threshold value meant to activate the whole neuron

A presynaptic nodes “A” and “B” must activate (or create) the node “AB”, which is not how bias works.  
Can only reiterate my crude visualization:

> **[Alex Semenov on LinkedIn: Myths of the Instance Based Learning](https://www.linkedin.com/posts/activity-7067534016710656000-tO6L)**
>
> Myths of the Instance Based Learning

---

<div class="post-metadata">

**Author:** ![neel\_g](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/neel_g/32/5503_2.png) [@neel\_g](https://discourse.numenta.org/u/neel_g)\
**Post date:** [August 17, 2023, 1:24pm UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/18 "2023-08-17T13:24:27Z")

</div>

yes… but having 1B parameters means nothing, when NNs can do this task with ~70M params. At the billion parameter regime, we get generalist models which can in-context learn. Those capabilities are missing here

---

<div class="post-metadata">

**Author:** ![Bullbash](https://avatars.discourse-cdn.com/v4/letter/b/e68b1a/32.png) [@Bullbash](https://discourse.numenta.org/u/Bullbash)\
**Post date:** [August 17, 2023, 1:38pm UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/19 "2023-08-17T13:38:55Z")

</div>

But 70M parameters belong to “faceless” nodes, associated with unexplainable real numbers mean nothing. Just parameters of equation.  
My 1B parameters belong to “self-labeled” nodes associated with particular patterns (Instance Based Learning). 1B can be reduced to 70M by careful selection, I’ve started the work, but have to drive my truck to Texas tomorrow. Will finish then back :-).  
The main point though, there are interesting symbolic operations over “named nodes-patterns” , “faceless” will stay pure stochastic forever. A shortcut to a dead-end. BP is not local.

---

<div class="post-metadata">

**Author:** ![Bullbash](https://avatars.discourse-cdn.com/v4/letter/b/e68b1a/32.png) [@Bullbash](https://discourse.numenta.org/u/Bullbash)\
**Post date:** [August 17, 2023, 3:38pm UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/20 "2023-08-17T15:38:17Z")

</div>

Intelligence is product of neural messages content, not the form. Carbon based protocols could be very different from silicon based. Thus there are two valid approaches:  
a) conventional-systemic studying “behavior of cells” and then understanding the neural code (carbon to silicon)  
b) risky - conjecturing of what content messaging might convey and experimentally checking completeness of the speculated code (silicon to carbon?)  
You do a) I do b).  
IMHO the set of “carbon behavior” features in my silicon implementations are most complete at present. One single engine/platform is: Hebbian-local, explainable (IBL), continually learning, multimodal, stable to drifts, structurally and synaptically plastic, maybe something else. It is late, got to go :-). Oh, well, it explains some psychological phenomena: curiosity, hypnosis, awe and sorrow. Too big a topic, so little time (c). Thanks for commenting, later!

---

<div class="post-metadata">

**Author:** ![dmac](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/dmac/32/5842_2.png) [@dmac](https://discourse.numenta.org/u/dmac)\
**Post date:** [August 17, 2023, 5:22pm UTC](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930/21 "2023-08-17T17:22:21Z")

</div>

Ohh, you did write down how your program works, it’s right here: [https://www.linkedin.com/pulse/myths-instance-based-learning-alex-semenov](https://www.linkedin.com/pulse/myths-instance-based-learning-alex-semenov)

That’s actually pretty neat!

If I could offer a piece of advice: you should take that blog post and turn it into a more complete article. I recommend putting a lot more effort into a one great explanation, instead of trying to explain your ideas ten time to ten different people.

About that blog post:

- I would add a sentence or two explaining the difference between instance based and model based learning.
- Also you should show a simplified example of how a sentence gets broken down into a basic tokens and how the basic tokens get combined into more complex tokens. In the example: label each neuron to show what it represents. A simple picture/diagram would help the casual reader.

[Next page](https://discourse.numenta.org/t/intelligence-is-embarrassingly-simple/10930.md?page=2)