# ML and Deep Learning to automatically create AGI?

**URL:** <https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501>\
**Category:** Machine Learning\
**Created:** [August 22, 2019, 3:11pm UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501 "2019-08-22T15:11:09Z")\
**Posts on this page:** 20\
**Page:** 5

<div class="post-metadata">

**Author:** ![yogaman](https://avatars.discourse-cdn.com/v4/letter/y/a9a28c/32.png) [@yogaman](https://discourse.numenta.org/u/yogaman)\
**Post date:** [September 1, 2019, 1:31am UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/81 "2019-09-01T01:31:21Z")

</div>

> [@Paul\_Lamb](#):
>
> How do you put pressure on a system to form general solutions rather than specializing toward only the tasks that it is being judged on?

I think you actually have to remove pressure to evolve GI.

Here’s my thinking. It’s a bit rough at this stage, so please be gentle.

TLDR: Give it a generalized reward mechanism for resolving a problem, and a “motivation” to treat some environmental states, as problems, e.g., threats, rivals, lack of food, lack of mate.

Longer version:  
It seems to me that the way we achieved human GI was by learning to solve lots of Specific Intelligence problems, then a few individuals with plenty of time in which to not flee, not fight, not pursue food or sex, etc., became habituated to the evolutionarily provided positive reinforcement mechanism that gives the Aha! reward when we resolve a query, answer a question, solve a problem.

I think this signal probably arises from the mechanism for recognizing when we have achieved those basic threat/rival/food/sex needs, but I suspect evolution has optimized the original signal in the presence of lots of non-primally motivated time. Keeping motivated and active when all basic needs are satisfied can be difficult, at least for some people, so we see people pursuing adrenaline rushes, food over-satiety, political power, sex addiction, substance addiction, and even abstract learning. All of these goal-seeking behaviors must be physiologically motivated.

Becoming junkies for that reward signal, which must exist for us to know when the goal is achieved, created the motivation and evolutionary reinforcement (because solving and avoiding more problems is evolutionarily advantageous) to apply goal-seeking-thus-problem-solving behavior from specific contexts to as many contexts as possible, so many that we have come to speak of it as General Intelligence.

Some might ask how we get an AGI to recognize new problems to which to apply itself. Well, our human GI recognizes new problems to try to solve because the evolutionarily enhanced reward signal has optimized for that behavior. Presumably, a reward signal for problem-solving in an AGI could perform a similar role.

---

<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:** [September 1, 2019, 1:52am UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/82 "2019-09-01T01:52:11Z")

</div>

I believe this sums up the thrust of your assertions:

> **[Maslow's hierarchy of needs](https://en.m.wikipedia.org/wiki/Maslow%27s_hierarchy_of_needs)**
>
> Maslow's hierarchy of needs is a theory in psychology proposed by Abraham Maslow in his 1943 paper "A Theory of Human Motivation" in Psychological Review. Maslow subsequently extended the idea to include his observations of humans' innate curiosity. His theories parallel many other theories of human developmental psychology, some of which focus on describing the stages of growth in humans. He then decided to create a classification system which reflected the universal needs of society as its b Ma...

---

<div class="post-metadata">

**Author:** ![yogaman](https://avatars.discourse-cdn.com/v4/letter/y/a9a28c/32.png) [@yogaman](https://discourse.numenta.org/u/yogaman)\
**Post date:** [September 1, 2019, 3:18am UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/83 "2019-09-01T03:18:17Z")

</div>

Thanks, but you seem to have missed what I’m saying.

My suggestion is that a way to get AGI is by implementing a human-similar reward for problem-solving. I do base my suggestion more or less on many of the needs Maslov offers, but don’t require his hierarchy or discussion of how to resolve conflicts among them, only that they are sometimes all, together-at-once non-urgent. I don’t recall Maslov discussing an evolutionarily developed need for problem-solving nor a reward signal for it.

---

<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:** [September 1, 2019, 3:25am UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/84 "2019-09-01T03:25:36Z")

</div>

The levels can be weighted based on how many are satisfied. The rewards don’t have to be static.

In this post I suggest that the lizard brain has a collection of states and as these states are asserted the cortex is essentially reconfigured. The success of each state should be evaluated independently to cut the evolution time.

> [@Low level processing in the old brain](https://discourse.numenta.org/t/low-level-processing-in-the-old-brain/6008):
>
> I have posted several times offering that the lower-level control structures work something like a Boltzmann or Hopfield network. I would like to expand on this concept. Let’s start with the basics. In the brainstem processing, we have many body sensors that sample blood-based messengers such as [osmotic concentration](https://en.wikipedia.org/wiki/Osmotic_concentration) or glucose levels. All of the body sensations also pass through these systems and provide additional information on the outside environment. It is the job of these low-level contr…

I cold see this general mechanism being applied to the organization implied by Maslow’s pyramid.

---

<div class="post-metadata">

**Author:** ![yogaman](https://avatars.discourse-cdn.com/v4/letter/y/a9a28c/32.png) [@yogaman](https://discourse.numenta.org/u/yogaman)\
**Post date:** [September 1, 2019, 3:52am UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/85 "2019-09-01T03:52:25Z")

</div>

Right. There must be a reward system. In particular there must be a reward signal, dynamic of course, for problem-solving activity, whether it’s at the level of a unicellular organism activating its cilia to move from a threat or object recognition by a fish brain. That reward signal for achieving a goal must exist. Without it, the goal is never achieved; the problem is never solved.

That signal, selected for by evolution because solving problems promoted survival, because it is a reward, eventually began to serve as a driver for some humans’ behavior. Presumably, those super-solvers had kids at a favorable rate, too.

Thus, the ancient End-of-Seeking signal from ancient goal-seeking behavioral mechanisms (originally based on primal drives) evolves to become the explanation for how humans apply Specific Intelligence in new contexts, which to me sounds like General Intelligence.

I propose that AGI might emulate that reward signal.

(Neurological levels? Maslov’s levels? Again, not interested in Maslov’s except when none of them are above threshold of requiring a response more “urgent” than the at-that-moment-ongoing pursuit of the problem-solving goal.)

Edit: Just saw your edit. I’ll read it now.

More edit:  
Nice writeup.

Where we seem to have not communicated is whether the increase of other drives is the only terminator for the presently active drive. I claim there’s an additional signal needed for the Aha! reward, and that it is the basis for the development of GI.

---

<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:** [September 1, 2019, 4:55am UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/86 "2019-09-01T04:55:37Z")

</div>

Example: drive hunger triggered by blood sugar moderately low and not engaged in higher priority such as fleeing predator.

Find food task  
Eat food task  
Terminator conditions gut full (leptin/ghrelin) or other condition rising above blood sugar trigger threshold . I think every drive has a terminal condition.

> **[Ghrelin](https://en.m.wikipedia.org/wiki/Ghrelin)**
>
> n/a n/a n/a

Each trigger condition could have variable thresholds. For example - very low food could overcome social drives. See: Les Mis!

Even social drives are still modulated by the lizard brain.

Curiosity serves to populate the goal map, and play - to populate the skills maps.

Oh - and that “ah ha” thing? Making the connection between drive and solution.

---

<div class="post-metadata">

**Author:** ![yogaman](https://avatars.discourse-cdn.com/v4/letter/y/a9a28c/32.png) [@yogaman](https://discourse.numenta.org/u/yogaman)\
**Post date:** [September 1, 2019, 5:43am UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/87 "2019-09-01T05:43:13Z")

</div>

I absolutely agree that subcortical structures are critical to motivation and behavior. I’m encouraged that you agree that every drive must have termination signal.

I agree that there can be different satisfaction triggers for lizard-level drives. I believe at some level of development there is a recognition of how the pleasurable sensation that a full belly creates is at least a little like other pleasurable sensations, for example, safe sleeping quarters. When the organism is “idle”, it can pursue one of the behaviors on its pleasurable list.

I suggest that in humans there is a more synthetic signal, one that gives rise to the “Aha!” sensation in mental problem solving. This signal promoted the behavior we call curiosity.

I didn’t discuss, but I believe the emergence of the Aha! signal is related to the need to process “mental” objects that emerge in social relationships, the most complex of which seem to be human. It’s not surprising (to me) that only humans might evolve the signal so highly.

My proposition only requires that signal and enough “down-time” from primal drives for the emergence of curiosity.

Curiosity expands the goal map greatly, but the goal map was populated before there was curiosity; before there were brains, organisms had goals.

Edit:  
I see you’ve edited again. Could you maybe please start a new post for new information while we’re typing back and forth?

I also edited for typos.

---

<div class="post-metadata">

**Author:** ![yogaman](https://avatars.discourse-cdn.com/v4/letter/y/a9a28c/32.png) [@yogaman](https://discourse.numenta.org/u/yogaman)\
**Post date:** [September 1, 2019, 5:45am UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/88 "2019-09-01T05:45:49Z")

</div>

> [@Bitking](#):
>
> Oh - and that “ah ha” thing? Making the connection between drive and solution.

Yes. Evolve that, and you get curiosity which is pretty close to GI, right?

---

<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:** [September 1, 2019, 5:50am UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/89 "2019-09-01T05:50:45Z")

</div>

Sorry about the multi-edit thing. When I am out walking it is difficult to check resources and I enter data that is all related in sprints. I happen to be out walking the trails at night at this moment.

Also - when I am driving around doing chores I have to set the phone down ( no distracted driving) and I close the edit window then.

Also - I spell check after posting and often see I missed a point I had intended to cover so it get added. Like this line.

---

<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:** [September 1, 2019, 5:59am UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/90 "2019-09-01T05:59:42Z")

</div>

As far as curiosity - lizards explore and establish territory.

This drive may be highly developed in humans but it is still an old-brain thing.

Any critter that has maps to goals will act to populate those maps with basic need goals like food, water, and shelter.

We humans are such chauvinists and tend to ignore that our most prized abilities are found in some form or other throughout the animal kingdom.

---

<div class="post-metadata">

**Author:** ![yogaman](https://avatars.discourse-cdn.com/v4/letter/y/a9a28c/32.png) [@yogaman](https://discourse.numenta.org/u/yogaman)\
**Post date:** [September 1, 2019, 1:42pm UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/91 "2019-09-01T13:42:56Z")

</div>

I usually agree very strongly that human chauvinism blinds us to the capabilities of animals with less cortex, but here you seem to be suggesting that lizard’s explorative behavior is equivalent to GI? I don’t agree.

Agreed, explorative behavior arises in lizards and in people when there are no more pressing drives. And lizards can apply skills from one activity to another in some limited ways. But only humans have generalized and developed curiosity to the extent that we have, at least for tool-making.

Something is responsible for the difference in scope that makes human-scale curiosity roughly equivalent to what we’re calling GI. If it’s not evolutionary refinement of the “Aha!” signal, what do you propose is responsible for the vast difference?

Edit: I hit send too soon. Sorry. I’d delete this post if I could. I’m hoping I can sneak in some edits before you see this. Sigh. Violating my own request in the first post after I requested it. Very sorry for the hypocrisy.

---

<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:** [September 1, 2019, 4:17pm UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/92 "2019-09-01T16:17:58Z")

</div>

No harm, no foul; I look forward to seeing your edit - when you do delete the edit thing and I will delete this bit. As for this post - I’m done now.

I am in no way suggesting that the drive to explore and the resulting curiosity is equivalent in lizards and humans. There is a continuum and this is clearly more developed in humans. Some of this is cultural and not in the hardware. I offer the example of speech and all it bring to the human mental machinery. [Without speech and the mental tricks it brings you lack the ability to form and manipulate certain mental constructs](https://discourse.numenta.org/t/language-the-base-of-conscious-thought/3629/5).

I do see AGI as far more than curiosity; I see that AGI will be a cluster of traits that must be taken together to seem intelligent.

- Intentionallity.
- [build in behaviors to act as a framework for development](https://discourse.numenta.org/t/project-full-layer-v1-using-htm-insights/3771/99).
- Memory. (it seems that several kinds will be needed)
- Task switching (with a minimum set of goals)
- Self awareness.
- Emotions of some sort (necessary for judgement)
- I’m sure if you think about it you will add a few more things to this list.

I have been posting on various aspect of this for a long time on these topics in this forum. I posted pointers to about half of them [in this thread](https://discourse.numenta.org/t/basic-system-level-diagram-of-the-brain/5834).

You may also want to read the thread " [Two Types of Hierarchies](https://discourse.numenta.org/t/two-types-of-hierarchies/6469)". There is some discussion relevant to this topic there.

As far as the “AH ha” experience, see [Global Neuronal Workspace](https://discourse.numenta.org/t/higher-level-regions-finer-tuned-motor-control/3589/3).  
To see this in it’s proper place, [see this post](https://discourse.numenta.org/t/temporal-unfolding-of-sequences/4082/22).

---

<div class="post-metadata">

**Author:** ![bkaz](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/bkaz/32/6455_2.png) [@bkaz](https://discourse.numenta.org/u/bkaz)\
**Post date:** [September 1, 2019, 11:48pm UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/93 "2019-09-01T23:48:45Z")

</div>

> [@yogaman](#):
>
> Something is responsible for the difference in scope that makes human-scale curiosity roughly equivalent to what we’re calling GI

I think that something is hierarchically recursive pattern representation, enabled by neocortex.  
Feedback of these hierarchical patterns is what guides exploration, physical or introspective.

---

<div class="post-metadata">

**Author:** ![yogaman](https://avatars.discourse-cdn.com/v4/letter/y/a9a28c/32.png) [@yogaman](https://discourse.numenta.org/u/yogaman)\
**Post date:** [September 2, 2019, 2:32pm UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/94 "2019-09-02T14:32:33Z")

</div>

@Bitking: Thanks for your encouragement to post the salient points from our recent emails. I think these are the points I made.

Solving the problem/query that curiosity generates produces an evolutionarily advantageous, behavior-reinforcing response. When curiosity’s reinforcement response is made more powerful curiosity can motivate behavior in a way that emotion does.

It’s possible to see this Aha!-response addiction driving some aspects of brain structure. The neural infrastructure that supports the evolutionary development of curiosity must support vast imagination capabilities as the range of consideration grows, optimally engaging as much of the neural population as allowed by physical constraints. Thus layer II/III’s long-range connections. But I do not make that claim at this time.

GWT seems fairly successful at modeling consciousness’s apparent serial nature, but people can hold conversations while folding laundry, so behavior is not entirely serial. I do need to study more about GWT.

Last, note that individual corvids, elephants, and top-of-food-chain predators, which are other notably curious animal groups, also have significant “free” time during which evolution could have sharpened the Aha! response.

---

<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:** [September 2, 2019, 8:47pm UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/95 "2019-09-02T20:47:11Z")

</div>

@yogaman

> [@yogaman](#):
>
> Solving the problem/query that curiosity generates produces an evolutionary advantageous, behavior-reinforcing response. When curiosity’s reinforcement response is made more powerful curiosity can motivate behavior in a way that emotion does.

I see curiosity as a drive to populate maps. In “lower” animals that is simple spatial maps of the environment (food, water, shelter, cached food) , predictor/prey facts, communications calls, and perhaps some social environment. (birds & pecking order?) These are learned extension of the built-in genetic programming.

As the number of interconnected maps increase you have the ability to form higher dimensional internal maps where the same type of objects have more abstract extents. These maps have the unique feature that you can explore them without having to move your body. These maps also need to be populated, hence the thing we call play and curiosity - the need to populate features about goal objects. As our representations become more abstract the definition of a goal object expands.

The Interpretation of GWT is a general mechanism. I don’t see that it has to engage the entire cortex with every activation. There are in excess of 100 maps, with two almost identical halves of the brain available. I could see local pockets of a few maps coalescing on some cluster of features & goal, with a different pocket elsewhere processing some other cluster of features & goal.

I think that the AH-HA feeling happens when a large number of maps fall into enlightenment with some (internally) important goal. These features could well be feature and relation aspects distributed through higher dimensional internal representations.

In case I did not make the point clearly - play and curiosity are drives like food, water, shelter, and reproduction.

---

<div class="post-metadata">

**Author:** ![yogaman](https://avatars.discourse-cdn.com/v4/letter/y/a9a28c/32.png) [@yogaman](https://discourse.numenta.org/u/yogaman)\
**Post date:** [September 2, 2019, 10:33pm UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/96 "2019-09-02T22:33:56Z")

</div>

> [@Bitking](#):
>
> play and curiosity are drives like food, water, shelter, and reproduction.

I agree that play fills maps, but I see play as a behavior motivated by curiosity.

Curiosity seems in a different class from primal drives such as food/water/shelter (shelter includes fleeing threats, right?). If those drives are not satisfied, the organism dies, yielding no (more) progeny. If reproduction is not satisfied before the end of an individual’s life, likewise, no progeny. If curiosity is not satisfied, the probability of direct impact to the individual’s reproductive success is minimal.

Consider also: In the simplest animals, enough information about how to select among possible behaviors seems to be available from birth. One might say their “maps” are pre-filled. (Maybe someone should carefully observe hydra for signs of play to test this idea.)

Curiosity as a motivation for play requires unfilled neural maps (assuming that neural maps are the repository for drives in more cortical animals). Simpler brains apparently have fewer maps to fill than human brains. It seems logical that the curiosity “drive” would be correspondingly weaker in those animals, unlike primal food/water/shelter/reproduction which would seem to be just as important to simple and complex organisms.

So it seems to me that the unique characteristics of curiosity as a motivator for behavior require an explanation for those differences. This has motivated my proposal for its amplification via the Aha! signal in free-time species.

Your suggestion to allow for \>100 maps seems to me to be an excellent enhancement to GWT, again given that I admit need for further study of GWT. If you have also considered how those maps interact, please share your thoughts.

I’m not sure you’ve significantly clarified the Aha!/AH-HA signal by saying it “happens when a large number of maps fall into enlightenment (perhaps you meant alignment here?) with some (internally) important goal”, more than just saying it signals the solving of the problem/query. What am I missing?

(I’m also not sure the antecedent for “These” in “These features could well be feature and…” or whether it’s more than tangential to your multi-map proposal.)

Finally, I’m making assumptions about what you mean by maps. Would you kindly point to or summarize a decent definition?

---

<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:** [September 2, 2019, 10:57pm UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/97 "2019-09-02T22:57:09Z")

</div>

Cortical maps 101:

> **[Cortical map](https://en.m.wikipedia.org/wiki/Cortical_map)**
>
> Cortical maps are collections (areas) of minicolumns in the brain cortex that have been identified as performing a specific information processing function (texture maps, color maps, contour maps, etc.).
> Cortical organization, especially for the sensory systems, is often described in terms of maps. For example, sensory information from the foot projects to one cortical site and the projections from the hand target in another site. As the result of this somatotopic organization of sensory inputs...

Region is a different name for a map:

> **[List of regions in the human brain](https://en.m.wikipedia.org/wiki/List_of_regions_in_the_human_brain)**
>
> The human brain anatomical regions are ordered following standard neuroanatomy hierarchies. Functional, connective, and developmental regions are listed in parentheses where appropriate.
> The limbic system, also known as the paleomammalian cortex, is a set of brain structures located on both sides of the thalamus, immediately beneath the medial temporal lobe of the cerebrum primarily in the midbrain. The classification of structures as part of the limbic system is historical and originates from...

And more about how they are connected:

> [@Grids into Maps!](https://discourse.numenta.org/t/grids-into-maps/3618):
>
> This is a companion to the post HTM Columns into Grids Sure Grids are cool - News Flash- so are Maps! The reinforcement within and between maps goes a long way towards a general solution of the binding problem. One of the “breakthroughs” for me is that the [cortical.io](http://cortical.io) people have formed the [SOM](https://en.wikipedia.org/wiki/Self-organizing_map) all in a single batch. While very powerful this is not biologically plausible; the brain learns online as data is presented to it. I am thinking that with an attractor model that is formed as the cont…

---

<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:** [September 2, 2019, 11:07pm UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/98 "2019-09-02T23:07:09Z")

</div>

The “standard” model of the cortex has a bidirectional flow of connections, one from the sensory areas towards the temporal lobe and frontal lobes, and the other roughly from the frontal lobes to the central sulcus with many projections back to the sensory areas. These projections from the frontal lobe are associated with goal states, and the sensory areas, perception of the environment.

---

<div class="post-metadata">

**Author:** ![gmirey](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/gmirey/32/2245_2.png) [@gmirey](https://discourse.numenta.org/u/gmirey)\
**Post date:** [September 2, 2019, 11:39pm UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/99 "2019-09-02T23:39:21Z")

</div>

Reading you with some interest.

> [@yogaman](#):
>
> Curiosity seems in a different class from primal drives such as food/water/shelter (shelter includes fleeing threats, right?). If those drives are not satisfied, the organism dies, yielding no (more) progeny. If reproduction is not satisfied before the end of an individual’s life, likewise, no progeny. If curiosity is not satisfied, the probability of direct impact to the individual’s reproductive success is minimal.

From what @Bitking posted here

> [@Bitking](#):
>
> This paper seems related to the current question of what initial functions you would give your evolving AGI to start the evolutionary process:  
> [https://link.springer.com/content/pdf/10.3758%2Fs13414-019-01760-1.pdf](https://link.springer.com/content/pdf/10.3758%2Fs13414-019-01760-1.pdf)

You may get another answer. Here expressed as a theory of a very basal eumetazoan

> [@](#):
>
> Here it becomes useful to make a distinction between two hierarchical levels within the nutrient control system (Fig.3B), which probably emerged more than 750 Mya. The ANS possessed chemical receptors sensitive to the nutrient content of the external world, which secreted hormones when that content was high. This defined a new lower-level impetus, “hunger + presence of food”, which motivated patterns of oscillatory activity at the blastopore that resulted in water intake.  
> […]  
> If the food was depleted before the hunger impetus was eliminated, the animal would now be in a state of “hunger + no food”, which would motivate oscillatory patterns at the blastopore that resulted in propulsion and, thus, long-range locomotion. This is analogous to “long-range exploration” and tended to have the effect of bringing the animal to sites of higher nutrient concentration  
> […]  
> Although the scenario described above is hypothetical,widespread evidence supports many of its features, including the signals involved in the internal causal pathways. In early eumetazoans, the high-level state was governed by the ANS,which in vertebrates became the hypothalamus, whereas specific behavioral policies (such as locomotion) were controlled by the BNS, which became the rest of the nervous system.Even in modern animals, much of the high-level control is still regulated by the hypothalamus. The general state of satiation is signaled by serotonin  
> […]  
> The shift between local exploitation and long-range exploration is governed by the neurotransmitter dopamine, whose secretion is related to food intake and which stimulates behaviors leading to area-restricted search in very diverse species, including nematodes, flatworms, mollusks, and vertebrates (Barron, Sovik, &Cornish, 2010; Hills, 2006). Indeed, as was proposed by Hills et al. (2015), the original role of dopamine may have been the arbitration of motor behavior between local exploitation and long-range exploration, and this was only later elaborated into the neurotransmitter’s many other roles in the vertebrate nervous system, such as the signaling of positive reinforcement (Schultz, 2004) and the modulation of **novelty seeking**

---

<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:** [September 2, 2019, 11:46pm UTC](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501/100 "2019-09-02T23:46:06Z")

</div>

> [@yogaman](#):
>
> If curiosity is not satisfied, the probability of direct impact to the individual’s reproductive success is minimal.

Success in exploration and mapping the location of food and water has a huge impact on the success in survival and would be a highly conserved trait.

Likewise - development of survival skills using play while still under the protection of a parent must offer a substantial survival advantage.

I could see this as the root of the extra-genomic transmission of information - culture.

[Previous page](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501.md?page=4)

[Next page](https://discourse.numenta.org/t/ml-and-deep-learning-to-automatically-create-agi/6501.md?page=6)