I first read Jeff Hawkins’ book “On Intelligence” 3 years ago and ever since then I have been fascinated to learn how we think. In order to learn deeper, I think building a biological intelligence simulator can verify my understanding. Since then I have been studying a lot of different papers, podcasts, and YouTube lectures. And I recently picked up the book again and re-read it to strengthen my understanding. I would like to utilize this forum to help me verify my understanding on how biological intelligence works.
So what is Intelligence?
Jeff Hawkins: “It is the ability to make predictions about the future that is the crux of intelligence.”. Agree. But it is the crux, not the entirety;
Einstein: “The true sign of intelligence is not knowledge but imagination.”. Also Agree. Imagination is important, but again not the entirety;
Robert Sternberg’s Triarchic Theory: “Analytical, Creative, and Practical Abilities.”. I think this is getting close. But not clear and precise enough for the perspective of brain building;
Bitking @ HTM Forum: “One method of definition is a laundry list of properties that will be present in an intelligence” https://discourse.numenta.org/t/intelligence-what-is-it/4802. Yes, we definitely need one. But I don’t believe the posting yield one?
So what is the laundry list of properties of what intelligence is in the perspective of building a software simulation of it? I can’t seem to find that list anywhere and I think it is important to define that list in order to build the product to achieve the objectives. So for my first post I am going to take a shot at it and hopefully others can critique (my ego is worth nothing, please critique as harsh as possible):
In my opinion, Intelligence consists of five basic elements intermingled together:
Perceiving Information
A starting point triggered by sensory input or “awareness”
Memorizing Information
In volatile memory then selectively to non-volatile memory
De-memorizing Information
In non-volatile memory
Predicting Information
Trigger existing memorized information from current occurring events through association to compare with the next occurring event and naturally memorize and de-memorize the information for the purpose of aligning the next Prediction with the next Perception
Deriving Information
Mash up existing memorized information with or without association to acquire new information. The ability to mash up is imagination and creativity.
Side notes:
I do not believe Emotion is a fundamental element in Intelligence. We can have intelligence without emotion. It is a nice-to-have, but not a must-have.
I don’t know the proper terminology for “awareness” (newbie problem), there has to be an internal mechanism for the brain to trigger thinking without any sensory input. i.e. Something triggers my brain to think now how the brain works.
The architecture has to be ultra efficient in terms of energy consumption and speed
As for the Purpose of Intelligence, I respect the spirit of Karl Friston’s Free Energy Principle:
Aligning the Prediction to match the next Perception to reduce energy consumption and increase the odds of survival
Thanks for the link. One thing I want to clarify first, since brain and intelligence are so complicated, I would like to be able to apply first principle to get down to the most basic and fundamental laundry list first. That is my objective for this first post.
So for “location”, I am not sure I would agree that is one of the essential elements to define intelligence. Say hypothetically a person is born blind and without limbs and unable to move his/her neck but his/her brain is functioning, I am not sure if that person will have the location model built in his brain but I am quite certain that person can be considered intelligent.
As for “reference frame”, I think I would agree if it is similar to memory association. I do have trouble initially with the terminology because reference frame, as a coordinate system, seems to be location related. For the reason I mentioned above I don’t believe location is a must-have item. However, I believe Jeff uses the term reference frame to mean something more abstract and can be applied to non-location related thinking and I think it is similar to memory association (I could be wrong though).
Please let me know your thought on this and I truly appreciate your help. Thanks.
You may want to rethink this point:
I do think that as much as most newbie AGI researchers would like to pull emotions out of consideration as an un-necessary complication - I see them as a feature and not a bug.
Note the key phrase:
In the Rita Carter book “Mapping the mind” chapter four starts out with Elliot, a man that was unable to feel emotion due to the corresponding emotional response areas being inactivated due to a tumor removal. Without this emotional coloring he was unable to judge anything as good or bad and was unable to select the actions appropriate to the situation. He was otherwise of normal intelligence.
You are coming at this like a programmer and not thinking of this with a wide enough view of the possibilities. The brain is all about memory but it does not have a space for memory to be recalled, processed and so forth like you relate - it all happens in the same place and at the same time with the same parts.
In this thread on memory I related that the process of perception is actually an act of active recall of prior memory fragments to match the current perception:
What is added to the existing memory is what is different, the delta of perception - the surprise in the perception.
As you may find if you dig around the forum, this has been the source of much debate. To save you some searching you can see some of that on this thread - with my two cents worth starting here:
This is really a very good topic. The definition of intelligence is very important. I have not seen a concise and persuasive definition in the forum so far.
If you have an accurate definition, you will have a correct theoretical framework.
My objective of this post is trying to get the laundry list to the very bottom without falling into the same fate as the European Human Brain project. So the question is Emotion part of the fundamental elements of intelligence. I think the key phrase you stated matches exactly how I understand emotion: “He was otherwise of normal intelligence”. My interpretation is without emotion, Elliot was still considered with normal intelligence. That tells me emotion might be an element of a smarter intelligence but not a fundamental element of intelligence. And by judging our daily examples like stock market and election and many other things, emotion often prevents us from thinking logically which also tells me that emotion cannot be part of the fundamental list. It will allow a species to survive longer (running away from predators, stay away from danger, pleasure to have sex to product offsprings, etc), but I don’t believe it is part of the most fundamental elements of intelligence.
I definitely try very hard not to have my background to form bias towards my understanding (but it is very hard).
I think maybe my wording on using “perceive” is wrong but as a newbie I do not know what word to use to describe the trigger point of intelligence such as photoreceptor or “awareness”. Let me know if you have a better word for this.
As for your statement:
I am not trying to emphasize on the “how”, I just want to identify what is the fundamental list of the definition of intelligence. What does the simulator have to achieve in order to have intelligence? So for example, if the simulator cannot memorize information, does it have intelligence? if the simulator cannot perform prediction, does it have intelligence? if the simulator cannot derive new information, does it have intelligence? If the simulator cannot be angry or afraid, does it have intelligence?
And based on my limited understanding on the “how”, I think I agree with you on
but this is a much deeper topic which I will save it for later after I can really identify the fundamental list of elements for Intelligence.
It is a very important topic and I won’t move forward until I get everyone’s help to really nail down the most fundamental list of elements for intelligence. And really appreciate your help on this and please continue to critique (and I will do my counter) until we can have a very very fundamental framework to proceed with the work. Super thanks for the all the help so far!
In all of the definitions I just offered above and referenced, some element of judgement is part of the definition of intelligence. You simply cannot make a decision without knowing if something is good or bad. Every experience that is encoded into memory is colored by some degree of emotion (something is good or bad) right along with the external perceptions. You can’t set this aside as some distant part of the brain; the emotion is baked right into the experience. It is a key part of common sense.
I like to think of isocortex as a database of sorts, where indices of data entries are sparse partial representations that invoke attractor dynamics throughout cortex, which are synced together because all things in the database were learned through joint sensory agency and interaction. Once stored, you can think of the isocortex as a simulation, where not only can you match external sensory perception to internal representations, but you can invoke internal representations at will. All representations are massively associative, so you can easily travel from concept to concept via “train of thought” associations.
You don’t have to be observing an apple to fire all the neurons that take part in representing “apple” in your cortex. You can just think “apple” and those neurons fire. You can invoke “apple” and place it in your visual field. You know how it feels in hand. You know how it tastes (are you salivating?). You can imagine in any way you like, anywhere you like.
We (Numenta) think this model in isocortex is a fundamental component of intelligence. It is the core of what makes us Human. It supports complex object modeling, language, societal constructs, etc. It enabled our civilizations to emerge. This is the type of intelligence we at Numenta are trying to understand and replicate in software. We are fairly certain that the models in isocortex are built with location in space at the core of the model. This extends a mechanism that evolution created to help critters* survive (navigate through world to find food / avoid death).
Yes, there is something else driving attention, no the isocortex is not isolated, it is highly connected to the rest of the central nervous system, but this model has a central circuit based on the representation of space at its core and it’s how we map all our abstract thoughts and constructions. Isocortex is not the only thing required to construct a useful intelligent agent, but it is necessary to replicate its function to construct a useful intelligent agent.
It is crucial to understand how isocortex works if you want to understand intelligence. That’s why we keep studying it.
* Yes I’m hijacking your word @Bitking because it works and it’s cute
I think a fairly obvious way to show location is fundamental is to realise that perceptional information only makes sense in relation to other information. This relation is the frame of reference.
The fact that so much hardware in the isocortex seems to be dedicated to produce this frame of reference (grid cells - displacement cells), tends to confirm this.
If such (unfortunate) person has any senses (hearing, touch), then there is hardly any doubt a location framework will be produced to structure all those inputs.
I’ve heard about this a few times in research meetings. Can someone explain this in layman’s terms? Is it related to the mathematical attractor?
I agree place is important. In evolution place is one of the first things an organism needs to be aware of and control. Also time. If I am a one celled organism I need to know where is the best food at this time of day and where is safe at this time of day. High in the water column or low column or in the mid level.
I am surprised I have not seen reference to palaces of memory the mnemonic technique of placing things (even abstract things) in a particular room in a fixed layout palace one keeps in memory.
The modular nature of all physical objects is well suited to 3D place mapping. The dogs tail is at the opposite end from the head and so on.
He have talked about it, in the video I posted with Jeff above, and our blog and even in the upcoming interview with Florian I think we talk that and simple verbal mnemonic devices.
I believe that “observing an apple” and “think apple” being distinguishable in this sentence highlights that they are perceived (and thus represented) in not exactly the same way (challenging the “all the neurons” assertion). They share some overlap in the neurons involved, but surely there are neurons which are unique to “observing an apple”, and which are not active during “think apple”, “say apple”, “hear apple”, etc. Even further, surely there are also differences between “apple” and “this apple”. All these should have varying ratios of overlapping to unique neurons involved.
