I've implemented a stacked Independent subpace analysis(ISA) network similar to the one in research paper mentioned below for unsupervised feature extraction. It consists of 2 ISA layers stacked one after another. Each ISA layer has two two layers in it. The first layer of the ISA captures square nonlineaity relationships in the input image patch. The second layer groups the response with respect to subpace size. It is very similar to Independent component analysis except it groups dependant sources together and these dependent groups are independent of each other. PCA is used at the beginning of each layer for dimensionality reduction.
My goal is visualize the features (weights at each layer) and the feature maps. Since the dimensions are reduced, the visualization is not straight forward. What is the best way for me to visualize the feature maps/features?
Also, how was figure 4 achieved in this paper?
Conference Paper Representation Learning: A Unified Deep Learning Framework f...
You can take a look at the following tutorial:
https://machinelearningmastery.com/how-to-visualize-filters-and-feature-maps-in-convolutional-neural-networks/#:~:text=The%20activation%20maps%2C%20called%20feature,preserved%20in%20the%20feature%20maps.
Fatemeh Abdolali For cnns it is quite straightforward since the filters are designed to be of the image shape. But in my case the output is not of an image shape. My input are patches of 3d images turned to blocks which is then fed to the network.
- Badges
- Science topic
- Similar topics
- Computer Science
- Images