The Limitations of Deep Learning • Hacker News Board

Re: The Limitations of Deep Learning

#271

Post by kxyvr » Tue, Jul 18, 2017, 5:07 PM UTC

beachbum8029 wrote: post #264

kxyvr wrote: post #163

Earlier quoted context omitted.

For the analogy to hold, it's more of a question of whether or not ML algorithms operate in the same way as the brain. Right now, ML models use algorithms from continuous optimization that require certain structure. Namely, we require a Hilbert space, so that we can define things like derivatives and gradients. This puts certain requirements on the kinds of functions that we can minimize and the kinds of spaces that…

Based on what goes on in every cell in our bodies when it comes to the information processing involved with DNA, I don't think there is any such algorithm which is fundamentally not realizable in biology. I'll grant you, I don't think biological neurons are calculating derivatives across connection strengths, but there must be some analogous process to control neural connection strengths.

That may very well be and I think it's a fantastic area to do research on. Namely, can we accurately model the body with an algorithmic process and what does this process look like? However, unless ML directly mirrors: the algorithms involved in the body, the models used by the body, and the the misfit function used by the body, which together already assumes that the body really does operate on a strict minimization principle, then I contend it's improper to anthropomorphize the algorithms. They're good algorithms, but a better name would be empirical modeling since we're creating models from empirical data.

Re: The Limitations of Deep Learning

#272

Post by randcraw » Tue, Jul 18, 2017, 5:13 PM UTC

taneq wrote: post #196

L_Rahman wrote: post #61

Earlier quoted context omitted.

I agree with your position. But I want to add a warning against the humanization of the brain. Many parts of it are complex in unknown ways, but some parts are truly mechanical. The parts of your central nervous system that respond to reflexes, that locate the source of sound or parse the color of retinal input are far more similar to deep learning algorithms than they are to what we think of as human consciousness.

> Many parts of it are complex in unknown ways, but some parts are truly mechanical. I feel like this is a bit of a false dichotomy. We've never encountered any spooky non-mechanical non-physical part of the brain, and we've been looking since Cartesian dualism was in vogue. What we think of as human consciousness is likely just a bunch of feedback loops allowing the brain to analyze some of its own state as if it we…

The same oversimplification could have been made of the visual system before we became aware of specialized cortical units and their federated/hierarchical arrangement.

In time I suspect we'll yet discover that much of the brain is inhomogeneous in unexpected ways and peculiarly interconnected. If it were not, we'd understand more about how it works by now.

Re: The Limitations of Deep Learning

#273

Post by visarga » Tue, Jul 18, 2017, 5:25 PM UTC

divideby0829 wrote: post #210

visarga wrote: post #105

Earlier quoted context omitted.

The author said in a Twitter conversation today that he is aware that this phrase is ignoring something essential - namely, that we have systems with memory and attention. That is something different than simple X to y mappings. With memory you can do general computation, recursivity, graphs, anything. They work well on some problems such as translation, but still need to become much better in order to match general…

considering they're the author of a python based machine learning library I would sure hope so. Still it seems like a pretty grievous oversight in writing the dang thing at all considering how at least in my fields of research memory-ful networks are increasingly popular.

It was reserved for part 2.

Re: The Limitations of Deep Learning

#274

Post by tsbertalan » Tue, Jul 18, 2017, 5:50 PM UTC

divideby0829 wrote: post #208

andreyk wrote: post #37

"Here's what you should remember: the only real success of deep learning so far has been the ability to map space X to space Y using a continuous geometric transform, given large amounts of human-annotated data." This statement has a few problems - there is no real reason to interpret the transforms as geometric (they are fundamentally just processing a bunch of numbers into other numbers, in what sense is this geome…

yeah this was my main problem, I guess he is technically right because they are geometric but many of his analogies like the paper crumpling were deeply misleading as they would imply that the transformations are linear. The fact that they are not is fundamental to neural networks working.

Paper-crumpling is nonlinear. Maybe your complaint is rather that paper-crumpling is "only" a topology-preserving diffeomorphism?

Re: The Limitations of Deep Learning

#275

Post by Florin_Andrei » Tue, Jul 18, 2017, 6:11 PM UTC

skgoa wrote: post #258

Florin_Andrei wrote: post #54

Earlier quoted context omitted.

> Pretty much every time DL is covered by media, there has to be some contrived comparison to human brains Well, what we've done so far is emulate maybe 1 mm^3 of brain matter - some isolated, very specialized functional blocks in the greater architecture of the brain. They behave as expected - are experts on very narrow topics, but of course fail to integrate their functioning with a larger body of knowledge, becaus…

You seem to be under the assumption that a typical feedforward DNN is anywhere close to operating like the brain, just on a smaller scale. But that assumption is not correct. Both the brain and artificial neural networks are connectivist, but that's about where the similarities end. The brain uses completely unknown algorithms and mechanisms that are almost certainly very different from our (current) ANNs. So it's no…

That is nowhere near what I am saying.

Re: The Limitations of Deep Learning

#276

Post by Florin_Andrei » Tue, Jul 18, 2017, 6:12 PM UTC

civilitty wrote: post #166

Florin_Andrei wrote: post #54

Earlier quoted context omitted.

> Pretty much every time DL is covered by media, there has to be some contrived comparison to human brains Well, what we've done so far is emulate maybe 1 mm^3 of brain matter - some isolated, very specialized functional blocks in the greater architecture of the brain. They behave as expected - are experts on very narrow topics, but of course fail to integrate their functioning with a larger body of knowledge, becaus…

> Well, what we've done so far is emulate maybe 1 mm^3 of brain matter - some isolated, very specialized functional blocks in the greater architecture of the brain. They behave as expected - are experts on very narrow topics, but of course fail to integrate their functioning with a larger body of knowledge, because that body just isn't there (yet). I think you're falling into the same anthropomorphism trap that the G…

I think you're far too eager to look for and criticize anthropomorphism - hence you see it where it's not.

Re: The Limitations of Deep Learning

#277

Post by randcraw » Tue, Jul 18, 2017, 6:16 PM UTC

pishpash wrote: post #76

kxyvr wrote: post #71

Earlier quoted context omitted.

I don't think so. There's an incredibly important art and science to model selection that is not encapsulated in curve fitting. For example, say we observe a boy throwing a ball and we want to predict where the ball will land. From basic physics, we know the model is `y = 0.5 a t^2 + v0 t + y0` where `a` is the acceleration due to gravity, `v0` is the initial velocity, and `y0` is the initial height. After observing…

You're talking about the complexity of the model. If you take a purely input-output view of the world (which by the way, even classical Physics does), every problem _is_ curve fitting in a sufficiently high dimensional space. There is no _conceptual_ problem here. There is perhaps a complexity problem, but that's why I wrote that "I think it's more hierarchical than that."

I disagree. Many problem spaces are not continuous and can involve incomplete information that make a continuous model like a curve useless.

For instance, a linguistic model that lacks definitions for some words, or which allows too much ambiguity can leave sentences unparsable or uninterpretable. Disruptions to word order in sentences can lose sufficient information that no curve or fitment can recover it. A curve has to capture sufficient information for fitting it to be useful. I think not all concepts or relations are amenable to N-dimensional cartesian representation. (Though I'd like to see a reference confirming this.)

And hidden interdependence between dimensions can make any curve drawn in that coordinate space a misrepresentation of the actual info space, and any curve fit in it, dysfunctional.

Any mapping of info onto a cartesian coordinate space presumes constraints that limit the utility of any function that across that space. So no curve is guaranteed to be meaningful in "the real world" unless those assumptions are conserved upon reentry from the abstract world.

George Box's "All models are wrong, but some are useful" suggests that while fitting curves in wrong models may be possible, it well may be form without function.

Re: The Limitations of Deep Learning

#278

Post by civilitty » Tue, Jul 18, 2017, 6:33 PM UTC

Florin_Andrei wrote: post #276

civilitty wrote: post #166

Earlier quoted context omitted.

> Well, what we've done so far is emulate maybe 1 mm^3 of brain matter - some isolated, very specialized functional blocks in the greater architecture of the brain. They behave as expected - are experts on very narrow topics, but of course fail to integrate their functioning with a larger body of knowledge, because that body just isn't there (yet). I think you're falling into the same anthropomorphism trap that the G…

I think you're far too eager to look for and criticize anthropomorphism - hence you see it where it's not.

You said "what we've done so far is emulate maybe 1 mm^3 of brain matter," comparing computational neural networks to us, a biological system - that's literally anthropomorphising.

Re: The Limitations of Deep Learning

#279

Post by randcraw » Tue, Jul 18, 2017, 6:53 PM UTC

I really enjoyed this article. It's the first attempt I've seen to assess deep learning toward the integrated end of human level cognition or AGI.

I found one point especially noteworthy: " So even though a deep learning model can be interpreted as a kind of program, inversely most programs cannot be expressed as deep learning models—for most tasks, either there exists no corresponding practically-sized deep neural network that solves the task, or even if there exists one, it may not be learnable, i.e. the corresponding geometric transform may be far too complex, or there may not be appropriate data available to learn it.

Scaling up current deep learning techniques by stacking more layers and using more training data can only superficially palliate some of these issues. It will not solve the more fundamental problem that deep learning models are very limited in what they can represent, and that most of the programs that one may wish to learn cannot be expressed as a continuous geometric morphing of a data manifold. "

What he seems to be suggesting is that a human level cognition built from deep nets will not be a single unified end-to-end "mind" but a conglomeration of many nets, each with different roles, i.e., a confederation or "society" of deep nets.

I suspect Minsky would have agreed, and then suggested that the interesting part is how one defines, instantiates, and then interconnects the components of this society.

Re: The Limitations of Deep Learning

#280

Post by mcbits » Tue, Jul 18, 2017, 7:06 PM UTC

somenewacc wrote: post #270

fnl wrote: post #206

Earlier quoted context omitted.

"Never" is a strong prediction. But yes, ANNs have nothing in common with BNNs (biological ... :-)) at all, other than taking them as a very rough abstraction for teaching the basic intuition of the chained up tensor transformations. The hard thing is to predict the when, or even if, of AI. If it will happen, it will be a sudden, light-switch like moment. I don't think AI can happen gradually. At least the first arti…

> If it will happen, it will be a sudden, light-switch like moment. I don't think AI can happen gradually. But our own intelligence happened gradually.

Human intelligence at the individual level evolved pretty gradually, but there hasn't been enough time for biology to explain our advancement in the last 10,000 years or 500 years. Culture and social organization are the essential nurturing factors there.

Every human genius would be out foraging for roots, perhaps reinventing the wheel or the lever, if it grew up without the benefit and influence of a society that makes greater achievement possible. Modern science and high technology that we attribute to human intelligence are really the products of a superintelligence (not to be conflated with consciousness) acting through us as appendages.

I think it's entirely possible (even likely) that all of the components of a new computational superintelligence already exist, but they are still "hunting and gathering" in the halls of academia or the stock market or biotech or defense...