New answers tagged

1 vote

Why do Convolution Neural Networks work on NLP/sequential tasks?

You can conceive images as 2D or 3D sequences of pixels. In the same way, text without any preprocessing or feature extraction is just a 1D sequence of words/characters. So there is no difference at ...
user avatar
0 votes

What architecture would be best to match images of torn pieces of tapes?

Why not try a Siamese network architecture? This architecture is used to compute the similarity between two inputs by applying the same neural network $f$ to two pairs of inputs $(X_b, X_p)$ and $(X_b,...
user avatar
1 vote

Denoise autoencoder not training properly

VGG16 is not trained to be used as an encoder for image reconstruction, it is trained to extract features from an image using which we can do classification task on the image. This is why, you cannot ...
user avatar
0 votes

How can I reduce the loss? Why do I have the high loss and why do I have the gradient?

There is something called Dead Neuron Problem in Relu Activation function which means if your weights becomes too small there will a time when your model will stop learning and there will be no ...
user avatar
  • 1

Top 50 recent answers are included