Transform Data by Example [video]

Post by fiatjaf » Thu, May 18, 2017, 1:07 AM UTC

Post by ChristianBundy » Thu, May 18, 2017, 1:14 AM UTC

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.

Post by paulddraper » Thu, May 18, 2017, 1:44 AM UTC

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.

Post by zitterbewegung » Thu, May 18, 2017, 1:45 AM UTC

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.

Post by nerdponx » Thu, May 18, 2017, 2:05 AM UTC

zitterbewegung wrote: post #18

function_seven wrote: post #11

Earlier quoted context omitted.

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.

Some ML systems (like decision trees) can give you a comprehenable way that they made the decision (would give you a list of if conditionals). Unfortunately many can't do this (random forests) . Having an AI that can explain itself in every situation why it does it also has to do with the underlying techniques. For instance random forests generate a random sample of the features and creates decision trees. So the exp…