Last I checked bridges came before Newtonian Mechanics and it seems strange to argue this wasn't a good thing. Admittedly paper writing wasn't the main mechanism of transmitting knowledge but it's fairly common for human engineering to come before the full theoretical foundations as opposed to after.
It's not that bridges before Newton were bad, it's that Newton gave us the ability to design the strongest possible bridge of a given shape with the materials at hand - using not just calculus but calculus-of-variations, a subject nearly as old as Newtonian mechanics [1]. With this knowledge, what happens when one adds one or two columns to a bridge is now longer "news" the way it might have been before Newtonian mechanics.
A stereotypical picture of an engineering approach without scientific knowledge would be a list of ways to do stuff combined with hints about how to vary the approach per-situation. It requires lots memorizing, trial-and-error and experts that often can't fully explain their reasoning. It's easy to believe bridge-building before Newton was like this though I'm not an expert. Present day AI sounds a lot like from what I've read (though I'm not an expert here either).
Edit: And yes, one could argue that the progress Newton ushered in merely replaced one list of models with a higher, more general list of models - yes, but that is how progress gone so far.
I completely agree with your assessment, but the problem is a bit worse in my opinion. We already have a pretty firm grasp of how different ML systems learn and converge towards a solution in the average case. It's not that we need to understand our neural networks better, it's that we need to understand our problem domain better. We can't determine how well some ML architecture will perform at an object recognition problem without some math describing object recognition. This makes things a lot more complicated, because it means we have to do a lot more work to understand every single application where we want to use ML.
And, of course, if we had some really good mathematical framework for describing and reasoning about object recognition, we probably wouldn't need to turn to ML to solve it ;)
The whole point of Deep Learning is that we don't want to describe math behind object recognition; it was the failed "classical" approach where people spent decades figuring out complex features which worked horribly. Deep Learning is actually pretty simple, well understood and parallelizable, and it's basically a billion-dimensional non-linear optimization. As optimization is infested with NP-hard problems, it's as difficult as it gets. It's actually amazing what we can do with it in the real world right now (and we are still far away from seeing all its fruits). Of course, it would frustrate academics that can't base AGI on top of it, but did they really think this approach would do it anyway?
Deep learning does not seem to abstract very well. Train on a data set then test with images that are simply upside down and the preformance can be significant.
Feature extraction also works much better when you toss a lot of data and processing power behind it. So, a lot of progress is simply more data and computing power vs better approaches. Consider how poorly deep leaning works when using a single 286.
> Deep learning does not seem to abstract very well. Train on a data set then test with images that are simply upside down and the preformance can be significant.
But that's true of people too. How quickly can you read upside-down?
If you trained on a mixture of upside-down and right way up images, and tested on upside-down images, performance wouldn't take that much of a hit.
Sure, the problem is we are more willing to ignore failures that are similar to how we fail. IMO, when we compare AI approach X vs. Y we need to consider absolute performance not just performance similar to human performance.
Deep learning for example gains a lot from texture detection in images. But, that also makes it really easy to fool.
While I can't easily read upside down text, I can instantly recognize it as not only text, but that it needs to flipped upside down in order to be read. That's something current "deep learning" AIs can't do reliably, if at all.
If I had to describe the root cause of this problem it would be that humans process "problems" rather than "things" and we "learn" by building an ever growing mental library of problem solving algorithms. As we continue to "learn", we refine our problem solving algorithms to be more general than specific. Compare that to a deep learning AI that learns by building an ever greater data library of things while refining algorithms to suit ever more specific use cases.
I think you're describing a level of generalization above the application at hand. We could easily train a neural network to recognize the orientation of a font, and then build an orientation invariant "reading" app by first recognizing the rotation of the text, transforming it so it is right side up, and then recognizing as normal.
I tend to imagine our brains works similarly. It's not that you have a single "network" in your brain that recognizes test from all angle, but your brain is a "general purpose" machine with many networks that work together. I think current deep learning techniques are great for discrete tasks, and the improvement needed is to have many networks that work together properly with some form of intuition as to what should be done with the information at hand.
It's not that we need to understand our neural networks better, it's that we need to understand our problem domain better.
How 'bout "creating models that can work with more dimensions of the problem domain than are conveyed by standard data labeling"?
I mean, we don't simply want AI but actually "need" it in the sense that problems like biological system are too complex to understand without artificial enhancements to our comprehension processes - thus to "understand the problem domain better" we need AI. If it's true that "to build AI, we need to understand the problem domain better", it leaves us stuck in a chicken-and-problem. That might be the case but if we're going find a way out, we are going to need to build tools in the fashion humans used to solve problems many times before.
It will probably play out like a conversation. A data scientist trains an ML model, and in analyzing the results discovers some intrinsic property or invariant of the problem domain. The scientist can then encode that information into the model and retrain. And that goes on and on, each time providing more accurate results.
As an aside, I think it's important that we find a way to examine and inspect how an ML model "works". If you have some neural network that does really well at the problem, it would be nice if you could somehow peer into it and explain, in human terms, what insight the model has made into the problem. That might not be feasible with neural networks, as they're really just a bunch of weights in a matrix, but this is practical for something like decision trees. Just food for thought.
This is somewhat practical for neural networks. For example, instead of minimizing the loss function, why not tweak the input to maximize a neuron’s activation? Or with a CNN, maximize the sum of a kernel’s channel? This would tell us what the neuron corresponds with. This is what Google did with DeepDream.
Now, I say somewhat because results can be visually confusing, ex Google’s analysis. Even then, we can see the progression of layer complexity as we go deeper into ImageNet. Plus, we can see mixed4b_5x5_bottleneck_pre_relu has kernels that seem to correspond with noses and eyes. mixed_4d_5x5_pre_relu has a kernel that seems to correspond with cat faces.
A data scientist trains an ML model, and in analyzing the results discovers some intrinsic property or invariant of the problem domain. The scientist can then encode that information into the model and retrain. And that goes on and on, each time providing more accurate results.
Mmmaybe,
It's tricky to articulate what pattern the data-scientist could see ... that an automated system couldn't see. Or otherwise, perhaps the whole "loop" could be automated. Or possibly the original neural already finds all the patterns available and what's left can't be interpreted.
The human participant may consider multiple distinct machine results, each a point in the space of algorithm, data set, bias applied to the problem domain. Human intuition is injected into the process and the result will be greater than the sum of the machines and a lone human mind.
What is interesting to note, now that above idea is considered, is that this process model itself belongs to the set of human-machine coordinations. Another process model is where low level human mind is used to perform recognition tasks too hard (or too slow) for machine to perform, for example using porn surfers to perform computation tasks via e.g. captcha like puzzles.
Long term social ramifications of all this is also interesting to consider as it motivates machines to breed distinct types of humans ;)
I imagine you need the data science to discern semantically relevant from irrelevant signals. How else do you “tell” your model what to look for? You could easily train for an irrelevant but fitting model.
It's work remembering that many times progress of held back by ideas that "aren't even wrong." The Perceptrons book wasn't wrong; it just attacked the wrong questions with an inadequate level of certainty in it's assumptions. It may be that we feel that we understand where machine learning is at now, but actually have a huge amount to learn because of inadequacies that we aren't even aware of.
Present day AI on the Deep Learning side is a lot like what you describe. We haven't really had the Newtonian foundations yet. The theoretical foundations are quite limited because they are hard to figure out. But the techniques with less established theory work far better on most applications in AI. Redirecting work into areas of AI that have more solid theoretical foundations but worse application performance is not the way forward. I'm all for figuring out hard theoretical foundations but I'm strongly opposed to redirecting research funding to techniques that result in worse applications. I'd also argue modelling the physics isn't always the right approach: vocal tract modelling for speech is an interesting approach that produces much worse speech than state of the art synthesis techniques. It will probably continue to do so for a long time. For vocal tract modelling to produce better synthesis you'd need the physical model to be less lossy in all it's parameterizations and modelling simplifications than any statistical fitting of data. And you'd still need some statistical model of the choices the human makes in producing speech and you'd want that statistical model to work better than the neural network that takes on a larger portion of the problem and replaces the physical model of sound production.
You're right that the analogy doesn't imply that something analogous to physic is the answer.
However, I would mention that there's a larger "overhead" than many realize to methods which work without the creator or the user understanding why. You have "racist" AI which don't undertstand that correlation may not be causation in questions like whether someone should be paroled or get a loan, you have the AIs subject to adversial attacks of various sorts, where not knowing why the AI works is also problematic, you have a situation where the target to match varies over time and so-forth.
Which adds up to AI having more dimensions to it than simply "working well" and "working less well". Indeed, AI is effectively ad-hoc statistics with result derived heuristically.
So in the process of "getting things right" exploring all sorts of things certainly sounds good, it seems like there's an "understanding gap" that needs to be closed and some broader model of what's happening would be useful but naturally there's no guarantee we can find one.
I should point out in this case it's almost certainly a genuine call to research the foundations underlying the working techniques more as Duvenaud publishes research using mostly the techniques that work well on applications.
It's been a long time since I got my BE in Mechanical Engineering, but I still remember being struck by the difference between well-understood engineering and rule-of-thumb engineering.
Bridge building is mostly well-understood engineering. When you study Static Mechanics [0] you learn all sorts of Physics equations, including Newtonian Mechanics, that completely describe the forces and motions of a structure based on measurable physical properties of the materials used and details about the shapes of those materials.
When you get into Fluid Dynamics, things are different. You start to encounter a bunch of things like Reynolds number [1], which is a dimensionless value related to turbulence that you just have to look up for the particular fluids and velocities you're working with. This number is pretty well defined, but there are a lot of others and their definitions and meanings aren't nearly as clear as F=ma. Back when I was in school, particle simulations for turbulent fluids was just beginning to be feasible, so to design something you plugged in dimensionless constants and didn't worry about the unpredictable fine-details. An example of this is the wind blowing through a bridge's structure, and water flowing around its base. The equations don't give you exact forces that the turbulent air and water will exert; they give you more of an average over time. A simulation, if you can do it, can show you things (like resonance) that the equations won't show you.
Then there was Strength of Materials. Here, the big thing was the Factor of Safety [2]. This is solidly in the rule-of-thumb engineering camp. This is where the engineer says "I think two 16" steel beams would be sufficient... so lets use three 20" beams just to be sure." This is still the way a lot of engineering design is done, because the real world is never precisely known, and the factor of safety will save you when something unexpected happens.
The "rule of thumb" engineering that you speak of made me remember the different constants that were taught we should just accept as is because, well, it is considered constant. Nevermind where the guy in the book got it from, this is what works and this is what people in the industry has accepted to be standard.
But a good degree should provide you with at least some of the insight and intellectual equipment to check for yourself or to smell a rat when you encounter a complex situation so that you can call for help rather than watch in horror as the house collapses on your clients.
