How to measure the quality of feature extracted from two neural networks?
If you use these extracted features to sovle classification problems, and the feature has less than 3 dimensions, you can visualize them in 3 three dimensional view to see the distribution of the samples; if the extracted feature has more than 3 dimensions, you can perform PCA or LDA to extract the top 3 components to visualize them in the 3 dimension-view to show their discriminative capability for different categories.
it's not obvious, but I propose to visualize the extracted features using multi output networks, it helps to set the layer where the features are extracted to be seen, and then you can compare the extracted features
Hello
Several methods can be used to assess the good quality of the features extracted by a deep network. You can maybe start visualising the extracting using some visualisation method (e.g. t-SNE), normally if your features are good, you should see the same structures as for the inputs, for example if you look for images, the images representing the same objects should be near to each other.. Another method to assess the god quality of your embedding is by investigating it capacity to classify elements of your dataset using a simple classifier (SVM, logistic regression...)
The best way is to compare these results with the true features (if they exist), or the detected by a human expert (if they not exist)
I suggest if you make a comparison with other classifiers i.e. SVM or K-NN. This is based on the type of your data set. You can also use any of the visualization methods to evaluate your outputs.
If you use these extracted features to sovle classification problems, and the feature has less than 3 dimensions, you can visualize them in 3 three dimensional view to see the distribution of the samples; if the extracted feature has more than 3 dimensions, you can perform PCA or LDA to extract the top 3 components to visualize them in the 3 dimension-view to show their discriminative capability for different categories.
- Badges
- Science topic