-
[Synthesizing the preferred inputs for neurons in neural networks via deep generator networks](http://papers.nips.cc/paper/6519-synthesizing-the-preferred-inputs-for-neurons-in-neural-networks-via-dee…
-
With baseline CNNs with no anti-aliasing, we see better shift consistency if we increase the CNN's depth, e.g. VGG11 -> VGG19, Resnet18 -> Resnet152. Why is that so?
-
Hi, there,
I noticed that in main.py we used the cv2.dnn. It seems we are using DNN, why this project is titled CNN in readme.md
-
http://doi.org/10.1101/067108
-
I have resort to the code of _Learning deep representations of fine-grained visual descriptions_, but their code is in Lua. And I have no idea how to get the CNN-RNN features.
Could you please offer…
-
# Description
@kingfengji Thanks for making the code available. I believe that multi-layered decision trees is a very elegant and powerful approach! I was applying your model to the boston housing da…
-
I want to implement 3D CNN with the CxxNet, but I am not sure whether the convolution is 3D convolution or multi-channel 2D convolution? More specially, If I have an image with MNK where M is the numb…
-
I am interested in Fully-CNN architectures to do handwriting recognition. I read your article "Searching from the Prediction of Visual and Language Model for Handwritten Chinese Text Recognition" whi…
-
From the query of @olerch below, there are a couple things regarding the estimator overview:
* a good first issue of reporting missing documentation and/or adding them to the respective API refere…
-
### Motivation and description
Is there such a thing as too many activation functions? I haven't decided on which of these, or if all:
**Natural Logarithm rescaled ReLU (NLReLU)**
https://arxiv…