Timeline for Can a convolutional NN be made with perceptrons?
Current License: CC BY-SA 3.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 8, 2017 at 17:48 | vote | accept | Thomas Wagenaar | ||
| Mar 8, 2017 at 17:39 | comment | added | GR4 | I just had a quick look at synaptic.js and the squash function. Note that they speak of neurons and not perceptrons. The point is that synaptic.js doesn't use the strict original definition of a perceptron, but uses neurons as building blocks to which non-linear activation functions can be applied. Under those circumstances: yes, you can reproduce the CNN with those building blocks. In fact, that is all a CNN is. | |
| Mar 8, 2017 at 17:30 | comment | added | Thomas Wagenaar | I like your answer, but what im saying is using a perceptron to calculate the hidden layer from a receptive field, which does not oupit binary data even when its just 1 layer. Im using a javascript library synaptic.js and depending on the Squash function, you wont have a binary output. I still cant see how it is not possible to create a CNN by the use (the same) of a perceptron for every detail that you want to pick up of the original input. | |
| Mar 8, 2017 at 17:27 | comment | added | GR4 | updated my answer to reflect this question | |
| Mar 8, 2017 at 17:26 | history | edited | GR4 | CC BY-SA 3.0 |
updated to clarify MLPs use to construct convolutional networks
|
| Mar 8, 2017 at 17:18 | comment | added | Thomas Wagenaar | Thats what I mean, ill edit it soon: the MLPs can be used to CONSTRUCT a CNN if I read everything correcty? | |
| Mar 8, 2017 at 16:39 | history | answered | GR4 | CC BY-SA 3.0 |