MATLAB Answers

How to design a locally connected layer for use in a convolution neural network??

7 views (last 30 days)
Michael Houston
Michael Houston on 27 Oct 2020
Commented: Michael Houston on 2 Nov 2020
I am trying to replicate the architecture found in this paper (https://www.nature.com/articles/srep36571), but the deepNetworkDesigner app does not have a locally connected layer. The best alternative I found is to use the 2d convolution but with 1x1 filter size to approximate the 1d convolution behavior (https://stackoverflow.com/questions/50388014/1d-convolution-for-cnn). According to (https://keras.io/api/layers/locally_connected_layers/locall_connected1d/) the locally connected layer is similar to 1d convolution, except the weights are unshared.
How can I go about actually making a proper 1d convolution layer?

  0 Comments

Sign in to comment.

Answers (1)

Srivardhan Gadila
Srivardhan Gadila on 30 Oct 2020
You can refer to Define Custom Deep Learning Layers & Deep Learning Custom Layers and implement your own custom deep learning layer.

  1 Comment

Michael Houston
Michael Houston on 2 Nov 2020
Thank you, Srivardhan. While I will definitely be using this to create the custom layer my main issue is the construction of the layer itself. I am not too familiar with deep learning but I appreciate any tips/hints to help me design the locally connected layer!

Sign in to comment.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!