New answers tagged

0

Yes, it is possible to change the filters of a CNN without a learning process, but you will obtain high accuracy when you notice that first layers filters should be more simple(for example they should identify parallel lines and etc), and each filter that belongs to a higher level should have a higher level of abstraction(should identify Alphabet, face,...). ...


1

What explains the apparent 'mirroring' of the graphs on the RHS, The model starts untrained and no better than random guessing (the baseline). As the training progresses, the model does better than random guessing on the training data, but does worse than initially on the validation data. The decrease in performance is because the data it is being trained ...


Top 50 recent answers are included