-
As the name suggests, the skip connections in deep architecture bypass some of the neural network layers and feed the output of one layer as the input to the following levels. It is a standard module …
-
I have been working through the gluon tutorials and found that in http://gluon.mxnet.io/chapter03_deep-neural-networks/mlp-gluon.html after the declaration of:
data_ctx = mx.cpu()
data_ctx is ne…
-
Hi, Denis.
Thanks for your effort on this lib.
I am trying to use this in my research.
However, it seems the learning rates of GRU and LSTM are all fixed after their initialization.
I want to cha…
-
I noticed that the current toolkit only supports Conv2D and Dense models. But in practical application and research, we often use time series data to predict. So I want to know whether this theory is …
-
### Deep Learning Simplified Repository (Proposing new issue)
:red_circle: **Project Title** : Social Housing Provision Analysis using DL
:red_circle: **Aim** : The aim of this project is to analyze…
-
Goal: Provide a type for use as both exchange and interop that represents multi-dimensional data if a single primitive Type. Implement arithmetic and linear algebra operations so that the type can se…
-
## 🚀 Feature
The blkdiag method is defined clearly in https://github.com/pytorch/pytorch/issues/31932
https://github.com/pytorch/pytorch/issues/31932 suggests blkdiag should create a dense Tenso…
-
This is for the same of implementing dense layers for neural networks.
The reverse pass also needs
`g.(Cbar) * B'` and `A' * g.(Cbar)`, but the fact that we have two instances of `g.(Cbar)` here m…
-
## 🚀 Feature
Support for Generative Models
## Motivation
**DGL** is intuitive to use and there are some great examples. However, **DGL** lacks generative models.
I am wondering whether there …
-
We should implement the PyTorch backend (#1014) and an option for full end-to-end differentiable operation so that [Neftci et al. (2019)](https://arxiv.org/abs/1901.09948) method can be used for train…