Timeline for Train a Neural Network to distinguish between even and odd numbers
Current License: CC BY-SA 3.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 28, 2022 at 10:48 | comment | added | Borun Chowdhury | This is a little misleading. If you convert the numbers to a binary representation then the neural network with a single layer would do as it can project to a space based just on the rightmost bit where the classes are linearly separable. The original question is more about what it would take for the lower layers in a neural net to put the intermediate representation in this form. Said different, one can ask for a neural network that gives the binary representation of a number. | |
| Nov 23, 2020 at 16:43 | comment | added | mxmlnkn | @Syncrossus Exactly that. This is just putting the answer as an input, so of course it will work. This solution does not generalize. The question is about divisibility by 2. Using binary representation most likely will not work when trying to train for the question "is it divisible by 3". | |
| Jun 7, 2019 at 11:59 | comment | added | Syncrossus | In binary, even numbers always end in 0 and odd numbers always end in 1. It's not surprising that the model works, since it's likely that it just learned to spit out the value of the last digit. | |
| May 30, 2019 at 20:36 | comment | added | Kaushal28 | Superb! This shows how the representation of data is important for any ML algorithm. When I used decimal representation, I got exactly 50 % accuracy, but following this idea, I got 100% accuracy even on unseen data. Thanks. Here is the implementation: colab.research.google.com/drive/… | |
| Jan 16, 2019 at 21:01 | comment | added | prosti | Exactly based on your answer I created the model in here stackoverflow.com/questions/53671491/… | |
| Aug 28, 2016 at 20:22 | review | Late answers | |||
| Aug 28, 2016 at 20:28 | |||||
| Aug 28, 2016 at 20:10 | history | edited | William Gottschalk | CC BY-SA 3.0 |
edited body
|
| Aug 28, 2016 at 20:07 | review | First posts | |||
| Aug 28, 2016 at 21:40 | |||||
| Aug 28, 2016 at 20:04 | history | answered | William Gottschalk | CC BY-SA 3.0 |