Timeline for Can multiple activation functions be replaced with a single activation function?
Current License: CC BY-SA 4.0
11 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 12, 2019 at 14:25 | vote | accept | VansFannel | ||
| S Oct 10, 2019 at 2:14 | history | edited | nbro | CC BY-SA 4.0 |
edited title
|
| Oct 9, 2019 at 18:57 | review | Suggested edits | |||
| S Oct 10, 2019 at 2:14 | |||||
| Oct 9, 2019 at 18:34 | answer | added | respectful | timeline score: 2 | |
| Oct 9, 2019 at 17:24 | answer | added | basilisk | timeline score: 0 | |
| Oct 9, 2019 at 17:19 | comment | added | VansFannel | I have updated my question. | |
| Oct 9, 2019 at 17:19 | history | edited | VansFannel | CC BY-SA 4.0 |
added 321 characters in body
|
| Oct 9, 2019 at 17:15 | comment | added | basilisk | you mean one activation function for every neuron ? | |
| Oct 9, 2019 at 17:08 | history | edited | VansFannel | CC BY-SA 4.0 |
added 78 characters in body
|
| Oct 9, 2019 at 16:35 | comment | added | respectful | Your question is a little unclear can you clarify: "I'm wondering if it is possible to have only one, and sum the output to all of the perceptrons, and pass that sum to an activation function." I think I understand but I want to make sure I truly understand your question. Do you mean is it possible to add another hidden layer with only one neuron? | |
| Oct 9, 2019 at 15:47 | history | asked | VansFannel | CC BY-SA 4.0 |