Abstract: Artificial neural networks are universal function approximators. They can forecast dynamics, but they may need impractically many neurons to do so, especially if the dynamics is chaotic. We use neural networks that incorporate Hamiltonian dynamics to efficiently learn phase space orbits even as nonlinear systems transition from order to chaos. We demonstrate Hamiltonian neural networks on a widely used dynamics benchmark, the Hénon-Heiles potential, and on nonperturbative dynamical billiards. We introspect to elucidate the Hamiltonian neural network forecasting.
http://www.catb.org/~esr/jargon/html/koans.html
In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6. “What are you doing?”, asked Minsky.
“I am training a randomly wired neural net to play Tic-Tac-Toe” Sussman replied.
“Why is the net wired randomly?”, asked Minsky.
“I do not want it to have any preconceptions of how to play”, Sussman said. Minsky then shut his eyes. “Why do you close your eyes?”, Sussman asked his teacher.
“So that the room will be empty.”
At that moment, Sussman was enlightened.
A baby is not born with the knowledge of body movement, for example, but through natural exploration of the body and environment, almost all physically capable humans learn to walk.
"We are seeking exceptional candidates to join our growing Autonomous Vehicle (AV) business team!"
https://techcrunch.com/2019/03/13/ford-is-expanding-its-self...
...oh that makes so much more sense! -.-
I'm probably misunderstanding what the accomplished, but it sounds like they've increased the accuracy of a neural network model of a system, notably for edge cases, by training it on complete a complete model of said system.
ML non-expert here. Is this the same as having an extra column of your input data that's a hamiltonian of the raw input? Or a kind of neuron that can compute a hamiltonian on an observation? Or something more complicated.
is this like a specialized 'functional region' in a biological brain? (broca's area, cerebellum)
Hamiltonian neural network (HNN) intakes position and momenta {q,p}, outputs the scalar function H, takes its gradient to find its position and momentum rates of change, and minimizes the loss
<latex equation for a modified loss function that differs from traditional NN>
which enforces Hamilton's equations of motion.
https://journals.aps.org/pre/abstract/10.1103/PhysRevE.101.0...
So, here it is: https://github.com/thesz/nn/tree/master/series
A proof of concept implementation of training neural networks process where loss function is a potential energy in Lagrangian function and I even incorporated "speed of light" - the "mass" of particle gets corrected using Lorenz multiplier m=m0/sqrt(1-v^2/c^2).
Everything is done using ideas from quite interesting paper about power of lazy semantics: https://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32....
PS Proof-of-concept here means it is grossly inefficient, mainly due to amount of symbolic computation. Yet it works. In some cases. ;)
Sutton is saying 'over a slightly longer time'.
You can wait 20 more years and super-duper-deep-NN-on-steroids, and hardware a million times as big and powerful, would rediscover all of theoretical physics.
Or you could inject some theoretical physics acquired by humans and make DNNs smarter today.
If so, this would be dramatic, no?
If you could teach a translation service 'grammar' and then also leverage the pattern matching, could this be a 'fundamental' new idea in AI application?
Or is this just something specific?
I don’t see a way to generalize this to the procedural rule-based systems you describe, unless they too are governed by a fairly simple continuous function Like the Hamiltonian.
I don’t know if it was “dramatic”, but it made me really happy.
Not quite. It's really just that they require the dynamics to be Hamiltonian, which would be highly atypical of the kind of dynamics an otherwise unconstrained neural network would learn. This is reflected in their loss function, the first of which learn an arbitrary second order differential equation, the second of which enforces Hamiltonian dynamics.
I don't understand how this was considered novel enough to warrant at PRE paper.
Here is a link to the paper:
https://journals.aps.org/pre/pdf/10.1103/PhysRevE.101.062207
In general the idea of including model or context-based information into neural networks goes along the line of Kahneman's System I and System II of the human mind. System I is the "emotional" brain that is fast and makes decisions quickly while System II is the "rational" brain that is slow and expensive and takes time to compute a response. Researchers have been trying to develop ML models that utilize this dichotomy by building corresponding dual modules but the major challenge remains in efficiently embedding the assumptions of the world dynamics into the models.
[0] https://arxiv.org/abs/1906.01563 [1] https://en.wikipedia.org/wiki/Thinking,_Fast_and_Slow
CSE researchers did not sit down and wait for AI researchers to learn the bitter lesson before they resumed their work.
CSE research goes on independent of whether AI/GOFAI/ML has a winter, a summer, an ice age, or a global warming.
It just so happens that in light of the recent progress of AI/ML, specifically 2012 to 2019, they see the utility of incorporating a tiny bit of ML to their vast array of methods.
The paper shared in this thread is merely another attempt to advance such an incorporation. If it doesn't pan out, they go back to doing CSE on physics without any AI or ML.
More generally, reptiles are born with nearly all the behaviors they'll need throughout life. Why wouldn't humans be born with some?
This is exactly what I'm talking about. Just like a baby deer "instinctively" can walk, but wobbles around for the first few hours, what you're seeing is something very similar to a purpose evolved neural network structure who's weights are being set through the principle of firing and wiring together (I forget what it's called).
I can't believe I got -4 for that!
Edit: hebbian learning. Point is it's probably far too much information to encode in DNA, but if you structure your neural network properly, you encode, how could I put it, the general topology of the problem you are attempting to solve, and through reinforcement learning "fill in the blanks" by training weights (or hebbian learning which functions similarly).
Brain scans of not-yet-born babies shows specific kind of brain waves.
1) Pre-existing structures that are already specialized for the necessary tasks, but untrained. We kind of mimic this with transfer learning, and by discovering more appropriate general architectures by hand.
2) Training while inferring. We very crudely approximate this by releasing updated models every month but I think it would be best if also performed at the edge. Google has begun doing this, I have hope for 'federated learning'[0].
3) 20+ years of exaflop training.
More narrowly focused to this article, I believe researchers keep finding that models which are architected to solve the most "general case" possible to solve consistently perform better on highly specific tasks than models trained only on those specific tasks. Definitely creating models that understand general physics follows that trend. Although I suspect, (as I believe you do), that scaling will be hampered without some sort of ML "fixed action patterns".
My thinking about this topic has been strongly guided by a special issue of Scientific American: Mind that I read in 2013 [1]. The issue was hard for me to find today because it's not listed in the usual archives, due to being a special edition. SCIENTIFIC AMERICAN MIND September 2013 Volume 22, Issue 3s
The whole issue is devoted to optical illusions and what they can tell us about how our brain uses evolutionary shortcuts to efficiently determine things in the real world. "In the wild", these shortcuts improve accuracy and speed of inference. But with artificial stimuli, they can lead us astray, and do in the case of artificially generated optical illusions.
As for the -4 (which is the maximum negative you can go on HN) I think some people just saw the first part and clicked downvote at that point.
> I don't think that's quite right. I believe that humans are essentially born as blank neural networks
I wouldn't worry about the vote counter. "Those who play for applause, that's all they'll get." -Wynton Marsalis' dad.
Following up like this to clarify for us idiots is really the best thing to do, maybe editing the original comment for clarity if you really feel like it.
0: https://ai.googleblog.com/2017/04/federated-learning-collabo... 1: https://www.scientificamerican.com/magazine/special-editions...
Anyone who's witnessed a birth can tell you this is wrong.
I agree that we are not born a blank slate, but at the same time, there's a lot of knowledge missing on a newborn baby.
There are a zillion skills, aptitudes, and personality traits more or less hardcoded in a newborn.
Which is why there is such a thing as "human nature" that is meaningful to talk about.
That kind of "human nature" that comes as a conclusion from the fact of what's hardcoded in a newborn baby is only a trivial kind, and not generally what people mean when they talk about "human nature" any more than the fact that babies are born with different eye colours tells us about human nature. Human nature, by definition, is found common to all humans, so a difference in "skills and aptitudes" does not say anything with regards to human nature (or the essence or appearance of it) other than "humans have skills, aptitudes and personality traits hardcoded" (which seems like a very strong claim to me anyway), but that itself would only be a trivial statement. It wouldn't tell us whether it's human nature (in the transhistorical, transsocietal sense) to be cooperative or greedy, violent or peaceful, etc.
Even so, understanding the fact that there is a human nature does not bring us much closer to what that human nature entails. Anthropologists, historians, economists, philosophers, and (some) evolutionary psychologists have a lot to say on the topic. To say that something is "just human nature" requires more evidence than "human nature is unchanging, applicable to all, and transhistorical".
Many modern people assume human behavior is an effect of upbringing and social cues. A mental model where it is a mix of upbringing and people's inherent human nature can be shocking to many.
Turkheimer's Three Laws of Behavior Genetics is a good world shaking introduction to this world:
https://teammccallum.wordpress.com/3-laws-of-behaviour-genet...
Many modern people don't mean everyone. The actual scientific literature on the nature vs nurture debate shows a surprisingly balanced picture which leaves some room for the hope of change. Still, defining human nature, and using it in a way which is non-trivial, requires a lot of work, especially the more abstract you go. Something along the lines of the quote, "To look at people in capitalist society and conclude that human nature is egoism is like looking at people in a factory where pollution is destroying their lungs and saying that it is human nature to cough."
Maybe we should be receptive to the arguments about human nature rather than (1) assuming it means what we think it does (2) assuming everyone who uses the term shares that meaning (3) assuming we know its essence and appearance right now.
For context, this thread started with someone saying I believe that humans are essentially born as blank neural networks, so that's what I'm arguing against.