Why Deep Learning surprises me
thevivekpandey.github.io
thevivekpandey.github.io
Ok, well I can also say "humans are just a bunch of chemical reactions and electrical signals."
The beauty of DL is in it's simplicity and really we're at the very starting point of seeing it work with extremely sparse networks (compared to biological intelligence). The fact that it works so well with such limited data in narrow domains should be energizing.
I would not argue otherwise, nor was this line of reasoning in question.
So you aren't arguing against my point, that reducing the argument of understanding to: "Well X is just [a, b, c]" is a bad argument. Instead you argue against the unstated claim that "X systems that look like they embody Y actually have an understanding of Y," in the sense that a human would "understand" Y. That is a strawman and not what the something I am claiming.
> reducing the argument of understanding to: "Well X is just [a, b, c]" is a bad argument
I think when you say, "humans are just a bunch of chemical reactions and electrical signals" you're stating a hypothesis, not a fact. But we know DL et. al. is just mathematical machinery.
It may turn out that consciousness is somehow the result of mechanics (I do not believe it, but that's beside the point) or it may turn out that what we are, the "thing" that understands, is somehow beyond mechanical systems. I feel like I should clarify that when I say "understanding" I mean more than that there is some mechanism that can perform a complex mapping from inputs to outputs (example: chess playing AI doesn't "understand" chess in the sense I mean.) There is some "self" that understands, and this is directly tied to conscious subjective awareness.
In one of your other comments on the same article you say:
> As to the question of consciousness, it is yet to be well defined, with no possibility to test (because of eg Qualia) so by definition you'd never verify or not. At most you'd recognize what you perceive as consciousness based on how you perceive other entities which you believe have it.
Consciousness cannot be defined, as you say, because it has no qualities. And it cannot be scientifically studied for the same reason. However, there is a method to "detect" it in other systems, to wit: merging. Two or more conscious systems can voluntarily merge, creating a new conscious entity partaking of but greater than its members. This isn't widely discussed or even known in AI and consciousness debates, so I wanted to mention it.
Sounds like woo-woo. Have any research on this?
I learned about it from (and I swear I'm not making this up) a pamphlet I ordered by mail out of the back of a comic book on "How to Read Minds". Much to my surprise, the simple technique it described worked. It turns out that thoughts are in a kind of space around us and the same faculty that we use to perceive "our own" thoughts can just as easily be used to perceive the thoughts "of others". In fact we don't have thoughts of our own, no one does, no more than a TV set has TV shows. Your brain has an ability to "tune" thoughts in and out, but they exist separately from us ourselves.
Cf. Kurt Gödel's description of how to "perceive pure abstract possibility" in http://www.rudyrucker.com/blog/2012/08/01/memories-of-kurt-g...
Now the sharing of thoughts deliberately (forming a thought and "sending" it to someone who is primed to receive it) aka "telepathy" is different than the merging of two consciousnesses into one consciousness. In fact there is only one consciousness, it is unitary, and the belief in separate identities is a perceptual structure founded in the ambient thought-forms. Separate identity is an illusion. So "merging" is actually a remembering of what is already the case, you just weren't paying attention.
There is one thing I can point you to: Dr. Charles Tart wrote a paper "Psychedelic Experiences Associated with a Novel Hypnotic Procedure, Mutual Hypnosis", but he's pretty woo-woo.
Anecdotally, lovers sometimes report merging during intense lovemaking. Many spiritual groups (associated with a religion or not) will tend to experience it during holy rituals. One indicator is group synchronicity.
The deepest experience of "one being looking through two pairs of eyes" is very rare, apparently, but lesser manifestations are pretty common.
In any event, if you can find a partner that wants to explore this with you, the technique is ultimately simple: Create the "set and setting" (peaceful, quiet, free from interruptions and distractions, and dedicated for the greater good of all), look into each others' eyes, and lower your inhibitions. That's it.
There are other factors that can help: breath together synchronously. Some people enthuse about cannabis or MDMA, etc., but they are not necessary, avoid them is my advice. Then again, if a glass of wine or a joint helps you relax and get cozy there's little harm.
What you're doing is forming a direct mutual feedback loop between your body/mind and the "other" person's body/mind. With practice and love this loop deepens until there is literally one organism in two bodies, carried by the feedback loops between the two nervous systems et. al.
I could go on, but that's either enough or too much already, eh? One thing to remember if you're going to experiment with this stuff, do it with utmost integrity. Just as Gödel said, "The ultimate goal of such thought, and of all philosophy, is the perception of the Absolute." Your ultimate goal must be towards the good.
"What do you suppose the input to the human brain looks like ?"
Since I have kids I have come to realize that the same thing you see in neural nets you see in human beings. Understanding exists, but it is mostly not how human beings respond to the world around them. Mostly we are a minimally generalized dictionary, we know a long long very damn long list of "tricks". If A happens, B will follow. There's very little along the lines of "objects fall along a parabolic trajectory".
This leads to generalization errors, and the surprising thing is you see those in humans ! Kids having learned to open one type of door do not know how to deal with an (even very slightly) jammed doorknob, they don't recognize differently shaped doorknobs as doorknobs, etc. First few days they don't even realize that if pushing won't work, pulling might. So the understanding of opening doors really does start out on the level of "move the free end of the small cylindrical object in the middle of the door that's parallel to the floor down, and then push", and if any of those conditions fails, well, door's going to stay shut.
And this is exactly the very hard problem you encounter with neural nets : finding the right balance between specificity and generalization. But one saving grace is that if you specialize in enough special cases, you can get around without having a general understanding, and that's exactly what's happening with kids.
The phenomenon is entirely well understood by all involved, and yet coming up with a reasonable definition is hard. http://existentialcomics.com/comic/164 So it's easier to be mystical.
Sometimes interesting things arise from many small, simple parts.
The question that it implicitly raises (at least, with me) is how can we tell the difference between 'understanding' and 'deep learning' if the end results are the same?
To me 'reasoning' is a slow, conscious process, and understanding is a part of that. But classification problems , especially when done by humans when they try to work fast have no room for such conscious decision making, we go much faster than that and outsource the job to our subconscious. Predictably, the error rate goes up and in those kind of situations deep learning can today already outperform humans on the same tasks.
The weird thing is that deep learning solutions can get simple cases completely wrong, where a human would never err, and yet get some of the hardest cases - where a human would be very likely to make an error - right. It's baffling.
That was his entire point.
What I wonder is whether that's not also maybe the cornerstone of human understanding. If I understand correctly, you are essentially saying that DL is forming categories, or developing a classification scheme. Granted, if we're only talking about supervised DL, and the program is practically told where to form the boundaries—then it's not very impressive. But if the software is extracting statistically prominent commonalities and using those to form category boundaries, and arranging them hierarchically—then while the implementation may be totally different from human understanding, the effect seems to strongly overlap.
I assume I'm probably just missing something—anyone know what it is? (It seems clear that at least part of the problem here is that 'human understanding' has been left far more vague than DL, and in order to say one way or the other how much they have in common, we need to better define 'human understanding'.)
There is one massive difference between humans and DL; humans can mimic something just from a single (even partial) observation; DL requires huge amounts of data and massive parallel processing, something that we got only recently with Big Data and GPUs.
DL also suffers from the curse of dimensionality; in theory deep fully connected networks should be able to do everything better, in practice they are awful and only cleverly constructed schemes like CNNs, LSTMs etc. that assume data to be in certain format/domain bring impressive results when paired with optimizers/metrics that magically work on a given dataset. If you are able to construct a DNN that can figure out PCA/ICA/eigenvalues/etc. on its own during its training like it does with convolutions, that would again enable another set of magic tricks. In any case, humans still have to figure out the architecture of the network that works (even if we now have AutoML for figuring out best hyperparameters in parallel).
Then the hard problem of consciousness; I personally believe we are far off and probably miss something very important in our understanding of Universe.
Exactly, and it's the fact that consciousness is outside of grasp of science (see my other comment in this thread).
Human learning is similarly based on large numbers of exposures; we don't form categories from single exposures. There are times where it looks that way, but what's happening instead is we come across a new particular instance of an already known general category (e.g. I have the general category 'cat', and I know they can vary on the dimensions, color, size, unruliness, etc.—and I've never seen a purple cat before, but I understand it after one exposure because it's just another value for an already known attribute. The less obvious examples are just super abstract, but have the same basic relationships in place).
> Then the hard problem of consciousness
That, by definition, doesn't have to do with any states of physical matter, nor any kind of computation. It's asking about the subjectivity of state transitions. So it should not be involved in considering a functional equivalent for (important subsets of) human brain behavior.
Edit: to clarify about the 'hard problem' relation to this: if you take Searle's 'Chinese Room' critique, for the question of functional equivalence it doesn't matter whether the person in the room understands Chinese or not; it just matters that at the end of the day the correct cards are held up.
Consciousness does come into it since we have a pretty visceral sense of it, and especially when we mentally trawl through our patterns to make some story, but really understanding should just be creating new patterns from existing patterns and the ability to utilize them as distinct entities in some way (rather than being emergent in the system implicitly and only being utilized by accident, say as emergent behavior randomly occurring because of local constraints)
You're underestimating what goes into high accuracy pattern recognition as well as assuming that patterns exist for only one vector and in a single context.
If I asked you to explain how you "understand" some concept, it will inevitably be how the structure and mechanics of it relate to others and in what context. All of those are simply patterns that are abstracted or made more granular.
For example, how do you "understand" what a car is? You would inevitably describe some definition of a car mechanically and the context in which a car operates. So it's a contained combination of metal and plastic objects and usually liquids with a mechanism to transfer power through gearing and wheels, a compartment for humans, some control mechanisms etc... (definition of the technical), but it can't operate in water (boat) or in the air (airplane).
Each of these things is learned through exposure over time, and recognized as connected, to come up with a "understanding" of a car even before it's formally defined. This is why children ask if cars can fly or go in the water.
Intelligence is not defined by the ability to recognize letters. Or play a game of Go.
Deep learning is a powerful tool for creating systems that have an ability to map inputs to outputs with very noisy, non-linear or complex data.
The mapping itself may be complex, but it's not going about solving problems like a person would. It has no idea what letters are, and how they fit into its world. It has no concept of self, cannot contemplate its own existence -- and perhaps most important of all, has no free will.
The moment we have some kind of deep learning or AI that has free will and can express interest in something other than what it has been trained on, I would say we are closer to unraveling the mystery of consicenesss and human intellect.
Even babies are animals exhibit many forms of free will, decision making, and novel behavior that cannot be explained with our current observations of route deep learning techniques.
Whoo boy not sure that's a good rabbit hole to go down. If you're unfamiliar with compatibilism I'd suggest you check it out. I think hard determinism gives the most reasonable answer here with a resounding no.
As to the question of consciousness, it is yet to be well defined, with no possiblity to test (because of eg Qualia) so by definition you'd never verify or not. At most you'd recognize what you perceive as consciousness based on how you perceive other entities which you believe have it.
A much more fruitful challenge to the aliveness of computers is to ask a singulatarian to show us any deep neural net that can fold proteins in constant time like physical reality can instead of exponential time like a computer algorithm can. Then I will believe that computers are alive and mind uploading is possible.
Or maybe I do. I'm seeing a glimmer but I don't want to put words in your mouth.
I suspect "What is consciousness?" will go the way of "What is life?". We more or less understand things that make up a bacteria. Those components aren't alive although the bacteria is. So, it's just a matter of definition.
Consciousness is misunderstood by surprisingly large number of smart people. The common view is that there's science and that's it, when actually, science just describes the patterns of what we observe via consciousness, which is in a way above science.
Regarding "what is life?", that's fundamentally different. Life can have fairly concrete definitions. Basically, it's a physical matter with specific properties, that's it. Whereas with consciousness, it's much more complicated. But defining, say, the feeling of pain as a physical matter with specific properties doesn't make much sense. "Pain is when these neurons are charged."
Also, what is a computation? A falling rock does perform a computation of a physical process. Any physical system can be said to perform a computation - or even a myriad of different computations, depending on how the physical state is interpreted.
If this was limited to chess, I would unquestionably agree.
If it was limited to image recognition, I would tentatively agree, although things like [0] make me cautious (admittedly, that was from March, and I'm not familiar with progress since then).
However, the author seems to be generalizing beyond those two domains, to the limits of human understanding. That seems like a couple-orders-of-magnitude leap too far to me. For example, I don't know of any autonomous system capable of understanding a short novel with simple language and writing a one-page summary of it, as might be expected of a human ten-year-old.
[0] https://twitter.com/Meaningness/status/846478348947668992
Humans being surprised by the computer should not be the yardstick for AI. A trained neural net can recognize the letter "A" and differentiate it from things that are not "A" but it does not know that "A" is part of the Latin alphabet and that there are other alphabets that form written human languages.
The day the computer spontaneously invents a new and usable alphabet without having been specifically designed to do so is the day I will concede we have hard AI. We have a long way to go. Until then it's just a bunch of hotdog/not hotdog classifiers.
There is nothing preventing the computer for learning those connections however, so all you are doing is moving the abstraction layer. It's not a fundamental break point.
Most humans have not spontaneously invented new usable alphabets, so I suppose that means most humans haven't meet the bar for true intelligence either.
I still don't understand this obsession for trying to define "hard AI" or "true intelligence" in binary terms. Intelligence is a spectrum, and deep learning has advanced it forward, thus making machines more intelligent -- yes, we can use that word 'intelligent' for computers just as we do for biological machines. Don't freak out.
Is it really so hard to accept that intelligence isn't all-or-nothing?
In your example a computer could very easily learn those simple facts, just like you did. It's nothing to tell a program how to classify a piece of data. You didn't use some crazy learning when you attributed A to being part of a Latin alphabet, someone just told you that fact and you saved it and classified A into the Latin alphabet.
Happened already at Google and Facebook. Namely Neural Turing Machines have created an intermediate language, that's a more efficent encoding, without being designed to do so. See: https://techcrunch.com/2016/11/22/googles-ai-translation-too...
But that's really old news and DNCs are more capable, afaik.
Some people push back on this by saying computers have no sense of self. Thats not true. Most computers do have internal state representations about themselves. Take a driverless car for example. When it does localization, it's constantly referencing its own shape and speed and comparing it to the environment. That's a sense of self.
Whatever philosophical barriers we place between ourselves and machines (and animals/nature for that matter), one thing is for certain: they will eventually debunked.
Instead, I like to think of consciousness in terms of structures and mechanisms of information flow. If we open our minds up to this type of thinking, we can see consciousness in varying degrees in nature, in computers, and of course in people. For anyone who's curious, the guiding light in this school of thought is Hofstadter's Godel Escher Bach.
Society as a whole has not assumed a concrete definition for consciousness, as there are a lot of people who don't give it a second thought. Among those who do recognize consciousness as such, the word "consciousness" is as close as you can get to being able to indicate the phenomenon. So I can't agree that it's not a helpful concept.
But in fact, the "thing" that is the referent of that term is not a concept at all. It is the pre-conceptual basis or arena for concepts that arise in it. The TV set is not a TV show.
Humans obviously vary in how conscious they are, both from one to another as well as individually over time so it cannot be properly defined circularly as you say above.
All "structures and mechanisms of information flow" are contents of consciousness not components. Awareness has no qualities, no form, no sides nor parts, it does not experience time: it is always "now", and it is always "here". What you are seeing "in varying degrees in nature, in computers, and of course in people" is mind I think. Cf. Gregory Bateson, "Mind and Nature: A Necessary Unity" and "Steps to an Ecology of Mind"
Lastly, "Godel Escher Bach" is an excellent book and was instrumental in my own process of coming to grips with consciousness. To wit: I think the closest we can come to modelling or describing consciousness mathematically is as a strange loop involving the entire Universe though-out all time.
In this case though, it is my opinion that there is no definite distinction between the two "types" of consciousness you are referring to. In my opinion, all consciousness exists on one vast spectrum. The distinctions between types are just constructs of human thought that were erected to preserve our sense of self and specialness as people.
I think the difference in type of question is like: if our universe is likened to a board game with some finite set of rules, e.g. Monopoly, the 'physics' of this universe is fully determined by the rules of the game (even if there are non-deterministic aspects where you have to e.g. roll dice). The non-hard problem of consciousness is a question in this realm, like "can I sell one of my properties to another player?"; the hard problem is necessarily outside the scope of the rules; it's a question more like, "what is the molecular composition of a 'Chance' card?". Unfortunately, the question is being asked inside of the game and all that's available in attempt to answer it are the constructs and rules from the game.
It's an interesting thing to consider because in some ways what it discusses is what we have the most direct empirical access to—and yet it's also one of the most clearly unapproachable topics which we couldn't usefully say anything definite about (except that its inaccessibility is interesting)
It applies to Deep Learning as much as it does Schank and Ableson's script understanding system.
The ability to introspect and analyse what makes that thing unique or understand what it's purpose or origin is has everything to do with being sentient.
We might not know what exactly being sentient is but recognising an image is like lobotomising the brain to just be a visual cortex, it can match but the other networks that work in the abstract are not there.
Meh.
Given enough examples, computers now can distinguish letter A and B but distinguishing is not understanding. You could argue that after learning the Network just uses an instruction set and from the outside that may leave the impression of understanding but it really does not. Isn't that basically the Chinese room thing?
A better way to summarize the central question of this paper would be: "Why is it that a large-parameter model trained with gradient descent on real data _could_ just memorize all of the training data (it has the capacity) yet finds solutions which generalize well to an unseen test set?"
To say that deep learning is _just_ memorizing its training data would be incorrect. We have empirical evidence to the contrary and this paper is part of that evidence.
Generalization is a multi-axis scale, not a switch: you can have more or less generalization in many different dimensions. Being terrible at adversarial examples just means that axis is weak.
What is there to understand? As far as I know the shapes we use for letters are arbitrary (at least at this point).
>"Specifically, we take a candidate architecture and train it both on the true data and on a copy of the data in which the true labels were replaced by random labels. In the second case, there is no longer any relationship between the instances and the class labels. As a result, learning is impossible."
This is like saying learning someones phone number is impossible because there is no relationship between the person and the number.
Memorization is pretty easy. Generalizing from past examples requires that there be a relationship not just between one person and their phone number but between all people and their phone numbers.