Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Transform Data by Example [video]

microsoft.com

Post reply on HN
Print view View original

81–90 of 94 posts

Re: Transform Data by Example [video]

#81

Post by jmmcd »

Houshalter wrote: post #73
jmmcd wrote: post #71

Earlier quoted context omitted.

No, it doesn't make sense. The training data (inputs and NN-predicted outputs) that you're feeding into the DT is at best the same as the training data (inputs and desired outputs) you had originally.

You can generate infinite training data with the NN by feeding in random inputs and seeing what outputs it gives. You can then train whatever model you want on it without concern for overfitting. But more importantly, the decision tree will model the behavior of the NN, not necessarily the original data. Which is what you want, if your goal is to understand what function the NN has learned.

The point about infinite training data is potentially useful. The other one I still don't agree with. Your goal is only to understand the NN insofar as it models the original data. Any errors the NN is making are not worth learning about. So it would be better to train the understandable method (DT) on the original data.

Re: Transform Data by Example [video]

#82

Post by sundarurfriend »

function_seven wrote: post #11
teddyh wrote: post #5

You know what this reminds me of? Those trained neural-net things which, however many training examples you give it, always seem to find some way to “cheat” and not do what you want while still obeying all your training data correctly. Something like this: Suppose we have a table of strings of digits, some including spaces, and we’d like to remove the spaces. From 123 456 234567 345 678 to 123456 234567 345678 Now, w…

This is why I want any ML device to be able to explain itself. It could train on your before-and-after examples and come up with a list of what it thinks you want it to do. For your example, it could list: “Remove interior spaces from each item” or it could say: “Remove the middle character from any 7-character strings to make them 6 characters in length” You would be able to do something with that.

This is the stated goal of the Explainable AI initiative, (spearheaded afaik by DARPA, though Google tells me corporates have also began work on it). I hope it works out well because there's going to be a lot of AI code in the near future, and the thought of them all being inscrutable black boxes is pretty scary.

Re: Transform Data by Example [video]

#83

Post by TuringTest »

Spiritus wrote: post #23
unfamiliar wrote: post #10

Humans are really good at taking a vague description of a task and using a small number of examples to disambiguate it. For example, "sort all of the folders, so that it Alan goes before Amy, etc". The rule ("sort") is pretty ambiguous, but one simple example in the context gives enough information to realise you probably mean alphabetically by first name. Is there something like this example that could be combined w…

Isn't just because we've already been trained on that since learning the alphabet? Imagine giving a human the same question, but sort "aa" before "bb" but after "cc".

Maybe it's "just" because of previous training, but it's still a very useful ability, which programs do not have.

Being able to solve quickly the most common cases (which rely in such "common knowledge") would automate a lot of work that now requires writing a complex program in advance, and would allow the user to concentrate on the outliers that require more thought.

Re: Transform Data by Example [video]

#85

Post by nilkn »

randomsearch wrote: post #45
nilkn wrote: post #31

Earlier quoted context omitted.

This might be a dumb question, but let's say that for whatever reason on a specific problem it's much easier to train a neural network that generalizes well than a decision tree. Why not train the network, then build an equivalent decision tree that just tries to reproduce the network's output? When building the tree from the network, overfitting would not be a concern. In fact, you'd want it to overfit. You could ev…

> This might be a dumb question, but let's say that for whatever reason on a specific problem it's much easier to train a neural network that generalizes well than a decision tree. Why not train the network, then build an equivalent decision tree that just tries to reproduce the network's output? When building the tree from the network, overfitting would not be a concern. In fact, you'd want it to overfit. You haven'…

I don't think I follow here. The goal of training the network isn't to encode the training data in the model, but rather to build a model that generalizes well. If the neural network has just memorized the training examples, then it overfit and really isn't useful in the real world.

I'm imagining a hypothetical example where generalization is easier to achieve with a neural network than with a decision tree using standard training techniques. Then a tree trained on the network might generalize better than a tree trained straight on the original data, with the additional benefit of being less of a black box than the network.

Re: Transform Data by Example [video]

#86

Post by thomasahle »

Giroflex wrote: post #36
teddyh wrote: post #5

You know what this reminds me of? Those trained neural-net things which, however many training examples you give it, always seem to find some way to “cheat” and not do what you want while still obeying all your training data correctly. Something like this: Suppose we have a table of strings of digits, some including spaces, and we’d like to remove the spaces. From 123 456 234567 345 678 to 123456 234567 345678 Now, w…

This isn't the machine's fault, though; for a small number of linearly independent examples there exists an enormous number of possible functions that match the training data. It has no way of guessing, really.

If the machine had a large background knowledge of what humans would typically like to do, it would help.

Re: Transform Data by Example [video]

#87

Post by teddyh »

function_seven wrote: post #11
teddyh wrote: post #5

You know what this reminds me of? Those trained neural-net things which, however many training examples you give it, always seem to find some way to “cheat” and not do what you want while still obeying all your training data correctly. Something like this: Suppose we have a table of strings of digits, some including spaces, and we’d like to remove the spaces. From 123 456 234567 345 678 to 123456 234567 345678 Now, w…

This is why I want any ML device to be able to explain itself. It could train on your before-and-after examples and come up with a list of what it thinks you want it to do. For your example, it could list: “Remove interior spaces from each item” or it could say: “Remove the middle character from any 7-character strings to make them 6 characters in length” You would be able to do something with that.

But, you know, if you saw something like, all your visible examples were like the strings

  123 456
  234567
  345 678
and the program replies with something like what you wrote: “Remove the middle character from any 7-character strings to make them 6 characters in length”, it would actually take a programmer’s mind to be able to envision why this might in some cases be wrong. Most people who are not programmers would, I think, see this as equivalent to “Remove interior spaces from each item”. I suspect that the skill required to choose an algorithm correctly is the exact same skill required to actually being a programmer.

All this then buys you is that you don’t have to remember the function names.

Re: Transform Data by Example [video]

#88

Post by Houshalter »

jmmcd wrote: post #81
Houshalter wrote: post #73

Earlier quoted context omitted.

You can generate infinite training data with the NN by feeding in random inputs and seeing what outputs it gives. You can then train whatever model you want on it without concern for overfitting. But more importantly, the decision tree will model the behavior of the NN, not necessarily the original data. Which is what you want, if your goal is to understand what function the NN has learned.

The point about infinite training data is potentially useful. The other one I still don't agree with. Your goal is only to understand the NN insofar as it models the original data. Any errors the NN is making are not worth learning about. So it would be better to train the understandable method (DT) on the original data.

>Any errors the NN is making are not worth learning about.

But that's the whole point of this method! To understand what errors the NN might be making. It's also quite possible the NN's errors aren't really errors, if there are mistakes or noise in the labels.

This technique has been called "dark knowledge" and is really interesting. See http://www.kdnuggets.com/2015/05/dark-knowledge-neural-netwo... They train much simpler models to get the same accuracy as much bigger models, just by copying the predictions of the bigger model on the same data. In fact you can get crazy results like this:

>When they omitted all examples of the digit 3 during the transfer training, the distilled net gets 98.6% of the test 3s correct even though 3 is a mythical digit it has never seen.

Re: Transform Data by Example [video]

#89

Post by jmmcd »

Houshalter wrote: post #88
jmmcd wrote: post #81

Earlier quoted context omitted.

The point about infinite training data is potentially useful. The other one I still don't agree with. Your goal is only to understand the NN insofar as it models the original data. Any errors the NN is making are not worth learning about. So it would be better to train the understandable method (DT) on the original data.

>Any errors the NN is making are not worth learning about. But that's the whole point of this method! To understand what errors the NN might be making. It's also quite possible the NN's errors aren't really errors, if there are mistakes or noise in the labels. This technique has been called "dark knowledge" and is really interesting. See http://www.kdnuggets.com/2015/05/dark-knowledge-neural-netwo... They train much…

Ah, very interesting! I agree that would be useful. But I think this thread has ended up with a proposal very different from the one I started replying to.

Re: Transform Data by Example [video]

#90

Post by tdbeteam »

matt4711 wrote: post #7

There is a paper describing such a method (not sure if that is what was implemented): "Zhongjun Jin, Michael R. Anderson, Michael J. Cafarella, H. V. Jagadish: Foofah: Transforming Data By Example. SIGMOD Conference 2017: 683-698"

No, the paper co-incidentally shares a similar name, but the capabilities are different, and there is no relation in terms of people or underlying technology. https://www.microsoft.com/en-us/research/project/transform-d...
Post reply on HN