Stanford Class on Deep Multi-Task and Meta-Learning
cs330.stanford.edu
cs330.stanford.edu
This is a good article on the topic: https://arxiv.org/abs/1902.03477
I've never before paid course numbers too much mind, but it does surprise me there's not yet some widespread standard of to help graduate admissions officers, graduate advisors, and grad students themselves when determining prerequisite eligibilty.
Recommend work & talks by Anna Gilbert for anyone interested. Entertaining & good at distilling technical content. Here is her most recent one, but there are other good ones on youtube. https://www.youtube.com/watch?v=Sb1ZhtsZjyM
Not to nitpick but that article is a year old and the field is moving at lightspeed
All in all, nobody really has a clue on how to do meta-learning right (or I am not aware of their work). There is progress being made on benchmarks, but some argue that progress is not really tackling the real issue at hand, i.e. learning to learn. Moreover, the current common benchmarks are not really good at untangling the progress in deep meta-learning from the progress in deep learning in general.
It is showing how you can get drastically better at deep meta-learning by being better at deep learning. But it does not really show how you can be better at deep meta-learning outside of the improvements in deep learning.
You can take any deep meta-learning algorithm, take the deep part in it, apply the improvements in deep learning from the last year and claim that you have improved on the deep meta-learning problem this year. Well yes, but actually also no.
It's like trying to find a new antibiotic, and the solution is throwing more existing antibiotics into the same pill. Well yes, it works, but it is also not exactly the problem.
Don't get me wrong though, GPT-3 is amazing work.
What new things will I be able to do after this course?
(in a practical sense, the technical description on the course page I can read myself)
I took a look at the course outline, and except for AutoML, it appears to be a one stop shop for learning multi-task and meta-learning. I just bookmarked the lectures on youtube.
Shortcut Learning in Deep Neural Networks
Did not get this part. I have limited sample of two kids, but I would say it takes at least a year before humans understand "cupness"
But, in general, deep learning requires far more examples to train image recognition and even then it's relatively fragile. (Not that humans can't be fooled but having models of the world in our brains help a lot. No, that's probably not a flying pig even though it looks like one.)
Than kids? Who have have video input 10h/day for years (~1B images) and can also choose their examples actively?
There are many ways in which deep approaches differ from kids (understatement of the year?), but to say that kids don’t see a lot of data seems not quite right. They’ve got a huge “world model” to draw on by the time they are good at one- or few-shot learning.
How many different cups are there in that dataset?
How many hours have I spent looking at cups? Anecdotally, my 2-year-old spends a huge amount of time playing with cups.
If I pickup a cup and move it around, pour water into it, turn it over so the fluid falls out, do it again, try some other object, compare them... how many data samples did I just receive in my 1 minute endeavor? The answer is: a lot.
Depending on how continuous (or not) space/time is and how fast your brain processes things... you're potentially being exposed to some extremely large discrete sampling of an infinite set.
How many actual discrete samples? Who knows, can probably come up with some bounding estimates with some work but that assumes we understand the brain better than we do. In addition, there's a reasonable amount of information that you likely inherit genetically so think about those massive discrete samplings over the time of your ancestors' lives and summarization and compression you get through evolution, over many thousands of years. The fact I have fingers, thumbs, and walk upright is a solution set found across a massive problem space and I get that out-of-the-womb (tm).
I don't believe modern ANN models are quite right and I suspect there's quite a bit we don't understand about our own intelligence that isn't or may never be captured here (hey, I want to be irreplaceable) but we have to consider the comparison more holistically.
One of the fundamental issues I believe DNN fail at is the fact they train against on high level problems and typically don't couple together for learning processes (it's not quite practical yet). As a human, when I learn how to do something I incorporate and connect it with future learning processes to help me learn faster or gain novel insights. Computationally this would be connecting stupid amounts of DNNs together in all sorts of ways (GANs are one line of thought similar here but I believe this would be a rich field to explore).
Personally, I'm completely against endeavors to search for a real AGI. I find it hard to believe once such a goal was obtained, it could possibly be good for my long term survival but hey, I'm a bit greedy in that respect.
Monads might be a good example of a thing for which humans don't have a massive headstart on ML due to "years of experience manipulating monad-like things" (as we do for most physical and social concepts). And I don't think anyone one-shot learns a monad.
Adults do (i.e. the agents pretrained holistic model of its entire observed physical context). By reducing the phenomenon to the single observation, you're conveniently ignoring the early childhood phases spent exploring shapes/3d-geometry that enable this very ability of inference. this isn't fair, because regarding humans, the line between training-phase and trained model is very blurry, whereas a statistical model is trained when the weights are set and done.
Brute forcing through 2d-projections of 3d-objects (further denormalized through camera-artifacts etc.) until something sticks in a convoluted (heh) composition of arbitrarily initialized set of nodes and connections is obviously far different from the physical exploration kids do. Comparing the models resulting from the latter with the former is, in a word, absurd.
Through exploration, humans develop a model of physics itself, from which the nature of cupness can be inferred (which is, in fact, the magic term).
Deep learning alone won't get us there, but it'll probably give us the components that enable us to simulate this intricate process happening in kids brains.
In fact, I'm pretty sure that that's what a lot of the smart people researching general intelligence are working on (because that's what I would do, excuse my hybris).
Well, that's what partly machine learning already does, right? :)
I think what I was looking at was the result that has been often observed, that progress in AI research roughly tracks with hardware developments. Looking at AlphaGo to AlphaZero to MuZero. Training time for self-play increases. But parallelism in the tensor units of the hardware is an order of magnitude faster. It's great for problem domains like autonomous vehicles, contactless payments in retail stores and fraud detection in the data center. But what about generalizability? What about the black box communicating how it has learned? Will it be suitable for next-gen applications like robots designed to assist humans in space expansion?
I attended an event in NYC around the creative use of AI by a new breed of emerging artists like Mario Kliegmann from Germany. ArtBreeder can train a GAN on a single input sample and generate paintings in the style of Fragonard or Picasso or Rothko. And someone made a remark along the lines of: "if this had existed in the 1960s, we wouldn't have need Warhol to invent Pop Art!". But in reality, Andy Warhol experimented with a wide variety of media and techniques. From film to "oxidation art". And it struck me that was the truly creative part of the process. One that arises from a place other than rational optimization on a single task or even multiple known tasks.