Category Archives: Uncategorized

Red Riding Hood in the Grey forest, a Noesis fairy-tale

In many of my posts, you’ve probably seen me use Noesis terminology to explain stuff, but I admit it’s hard to keep up and sometimes if you don’t have the concept handy in memory, you may get lost or misinterpret the message. For this reason, I’m gonna tell you a fairy-tale; that of the Red Riding Hood sisters (they are many 🙂 and their trip to the Grey forest.

So the Red Riding Hood wants to go to the cabin, to meet her grandmother. But the Grey forest is a actually a maze! There are many paths, all convoluted and you can never be absolutely sure that you’re going in the right direction. On top of it, it’s night, and it’s dark! Little Red Riding Hood is carrying a lantern, but the light it sheds is of course omni-directional, and cannot see very far towards one direction.
So it’s worst case is when the path she’s travelling on ends on crossroads. Her little lantern may not be enough to shed enough light towards the alternative paths, so she’s unsure where to go. Her past experience ("follow the straight path up to where it leads you") is not enough to judge how to continue. Little as she is, her only solution is to start crying (in Noesis terms: a Driving Pocket – DP). The more lost she is, the more loud she will probably cry (how big the DP is).

But fear not, because there is a chopper patrolling the woods (in Noesis terms, this is the Battery), and is actively listening around, eager to help if any of the Hood sisters is at a loss. The chopper has big directional lights, so when it hears the cry for help, it quickly flies on top of the little Red Riding Hood and uses its lights to illuminate the various alternative paths (i.e. we focus our attention and try to identify Action Pockets). With this big help, little Hood can now orient herself. As soon as she has a good enough idea of which is the best path to follow in the crossroad, she starts walking towards it (what we call fuzzy routing).
This way the chopper can be decommissioned and go help another one of her sisters, that may also be crying for a similar reason at another part of the forest! In the end we have one chopper for the whole forest, so it would be unfair for the one sister to monopolize its services. That’s why it’s important to make up her mind quickly and start walking towards a path (i.e. the importance of fuzzy routing to not get the full attention for long). Because in any case, if the little Hood finds out that her hasty decision was the wrong one and she didn’t pick the correct path, all she has to do is start crying again and the chopper will arrive again at her assistance.

Finally, there may be some cases where there are more than one sisters crying together at different parts of the forest. What does the chopper do now? Simple, it will go to the sister that is crying louder! Because it means that she’s in more trouble.

Why we think

It may be a question so basic, to the point that is sounds stupid. After all, the thinking process is so abundant in humans in everyday life, so it’s considered from granted. We cannot even think of ourselves without the capability of thinking (sic); we wouldn’t exist without it, right? (cogito ergo sum). At the same time, we have to admit that humans, as the cornerstone of evolution has managed to upgrade the thinking process so much that it is now capable of juggling with extremely complex topics, such as the structure of the universe, the meaning of existence, the inner workings of the human mind, etc… This level of complexity can defocus us from the most primal purpose of the thinking process, the one that evolution favored and thus granted us with the ability to think.

In terms of Noesis Theory, I have outlined in a previous post the main mechanism that I think the brain uses, which is to utilize past experience (the past) in order to translate the incoming stimuli (the present) into the most preferable potential outcomes (the future) and try to bring this future into reality.
When you connect the mechanism of thinking with the description above, it’s very easy to link thoughts to "the future". In other words

the mechanism of thinking was given to us in order to be able to predict the future.

The act of thinking is in reality a projection of limited info we have into what could be; into a future.
So when I converse with you and mention the word apple, you will probably bring into your mind the picture of an apple, into your mouth the taste of an apple. Why? Because back the jungle, when you heard the sound of flowing water (thirsty after some hours of scavenging), via your thought process you would be able to predict a candidate future of you finding this spring and drinking its refreshing water. This would be translated as a preferable future, and you would therefore strive to make it a reality.
So we are programmed to experience one thing and immediately think what can come next, and how we can turn this into our benefit. That’s why we "were granted" thinking by… evolution. Our inner vision/smell/taste/hearing, our imagination, it’s there to envision the future.

You might argue that there are all too basic things that I’m describing. That the modern homo sapiens has a much more advanced thinking ability. I can agree with you, but I would also add that this is just (much) better pattern matching, overlaid on top of the very basic evolutionary mechanism that I described. Because the core principle of guessing the future (in order to pick the most favorable one) should be the foundation for thought. In fact, I would even guess that for the same reason all animals with a relatively complex brain have the ability to think. The main difference should be located in their ability to grasp abstract concepts and link distant patterns via the pattern matching capability of their brain. But the core principle (and evolutionary need) of thinking should remain the same across all non-simple living beings.

Are we willing to have forgetful machines (AI)?

When we think of machines, we immediately bring determinism to mind. Machines are cruel, they’re full of 1s and 0s. There is nothing in between. No emotion, no variability, no grey areas. They are governed by facts, and they can store a vast array of them; many, many times more expansive than what the human mind can deal with. That is, with existing machines.

The thing is, when we’ll try to transition to true AI, this model will have to change drastically, due to a fundamental paradigm shift: True AI is foremost about true learning (and by this I mean autonomous learning, without cheating by injecting predigested human knowledge). And true learning necessitates forgetfulness! The modus operandi of the human mind, “if you don’t use it you lose it”, is quintessential for advancing our learning and comprehension.

You almost never learn something first time right. You need to experience several similar circumstances and have repeated attempts, at different angles, to build solid foundation of how you can tackle with a situation and all similar to it. That’s why you need to forget in the meantime, every time. Parts of the approach that worked every time will remain in your working knowledge, and you’ll reuse them. Parts that worked once but not many will be forgotten and leave room for other, novel approaches that may prove more successful. In the end, when you’ve build a solid foundation and learned this thing, it will be because you kept the best of everytime and laid the groundwork that can handle more or less successfully every upcoming iteration. You allowed through forgetfulness to “prune” the tree of knowledge, keep only the strong branches, and thus give the opportunity for growth to new branches, which only if they are proven equally strong will be maintained. Forgetfulness is essential thus. Else your learning progress would quickly become deadlocked, because in the first “wrong turn” you would reach a dead-end and would be unable to backtrack and start afresh.

The reason I elaborated so much on this is because when we’ll finally be ready to built true AI, we’ll need to implement the same mechanism of forgetfulness (alas, we know no better) and the result will be… robots… that will be unlike everything we’ve been imagining all the past decades. So far from determinism, but also so familiar, because they will be almost human in some ways. And the question is, are we ready to accept such an invention? Is it possible that humanity will be underwhelmed, because it was expecting something almost superhuman? Will the potential usage scenarios that we’re building in our fantasies & science fiction just collapse and have to be rebuilt from scratch?

Probably not, but it’s an interesting question to ponder.

We’ve got it wrong: we learn by error&trial not trial&error

It seems we got it all wrong in the first place! It’s the reverse. We learn to do such by error & trial, not trial & error! I.e. first and foremost we err; and only then we try to fix this error.

If we use Noesis Theory terms to explain in a bit more detail:

at first, we receive a pattern but have no idea what it means to us (in terms of pleasure/pain). I.e. we’re about to “bang our head into the wall” and don’t know it until we feel it. Once we receive the feelings of pain (or pleasure), the error, and a DP is created, then the incoming stimuli that was experienced just before is linked (feedback) to the DP, i.e. this pattern gets an “emotional coloring” as I like to call it.

Next time we experience this (or a very similar) pattern, the traversal in our brain will be quick enough and will activate (somewhat) the DP before we actually feel the pain. This will be enough to activate our attention and make us try to avoid it (or enhance it if it’s a pleasure).

So in summary, first comes the error, and next time comes the trial to avoid the error. So a child first will feel the pain of the error of stepping on a toy car in his path and falling down, and next time it will make a trial to avoid stepping on it. That’s the way it learns. This means that we got it all wrong in the first place! It’s error & trial, not trial & error! 🙂


Of course I’m writing the above with a playful attitude and I’ve kind of skewed the original target of the “trial & error” motto. If we target it in its original direction of problem solving, of course trial & error still stands. But until we err, we don’t have an incentive to do trials, so I wanted to illustrate in this manner that the precursor of a trial & error session is indeed an “error & trial”, that provides the root cause for starting it.

I reject your reality & substitute my own

It’s funny, but if I had to pick a quote that best describes in a succinct manner how the human brain functions, I would pick this phrase, as popularized by Adam Savage:

I reject your reality and substitute my own

The reason it’s funny is because this phrase was probably intended as a pun, but the irony is that, in the end, this is the main utility of the brain!

The brain predict what will happen, evaluates whether it will be good or bad (emotional coloring, as I like to call it) and if it believes there is something to be gained (a pleasure to capture or a discomfort to avoid) it chooses a different reality and starts projecting it as the preferred alternative! And the way the brain circuitry works, the more it projects this reality the more likely it is to start happening. Actions happen, thoughts are done and it gets closer and closer to this new, preferred reality.

In other words, it rejected the reality that was presented to it, and attempted to alter the environment to substitute the reality with its own!

 


 

I’ve made some good progress with Noesis. I’ll come back and try to explain it even better with the mechanism that this whole thing implements, so that it’s even simpler to understand and follow along.

Cheers, Vassilis

%d bloggers like this: