Timeline for What is the trade-off between batch size and number of iterations to train a neural network?
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 12 at 19:00 | comment | added | Boomer | "In this case you know exactly the best directly towards a local minimum" - is not entirely correct, as cited by @Franck Dernoncourt: "Also, if you think about it, even using the entire training set doesn’t really give you the true gradient ... Using the entire training set is just using a very large minibatch size" | |
| Oct 15, 2021 at 17:44 | history | edited | David Parks | CC BY-SA 4.0 |
minor typos
|
| Dec 13, 2018 at 18:01 | history | edited | David Parks | CC BY-SA 4.0 |
added 7 characters in body
|
| Feb 20, 2016 at 20:55 | history | answered | David Parks | CC BY-SA 3.0 |