New answers tagged

0

You are right! 1- the number of hidden layers shouldn't be too high! Because of the gradient descent when the number of layers is too large, the gradient effect on the first layers become too small! This is why the Resnet model was introduced. 2- the number of hidden layers shouldn't be too small to extracts good features. It's proved that in CNN networks ...


0

It depends on your image size and the size of the compression you want! Usually deep learning algorithms are not so fast as why they run on GPU, and we have highly optimized frameworks like TensorFlow! Something I can say for sure is: Compressing video using autoencoders means compressing each frame one by one! However, video compressions usually contain ...


4

Auto-encoders are widely used and maybe even more used than GANs (in fact, auto-encoders are older than GANs, although the main general idea behind GANs is quire old). For example, auto-encoders are used in World Models, for drug design (e.g. see this paper) and many other tasks that involve data compression or generation. So, if we train autoencoders, for ...


1

There could be multiple possible ways to extract the features. One would be to use RNNs for a temporal relationship as the input data is time-series.


4

In fact, autoencoders are used for generative tasks. Have a look at Tutorial on Variational Autoencoders (VAEs). The coolest thing about VAE is that abstract features can be easily amplified or suppressed based on extracted vectors from the latent space. Let's imagine a model trained on MNIST to generate digits. If you take two images of the same digit which ...


Top 50 recent answers are included