-
**Describe the bug**
SGD produces nans when using its predict method on the Kaggle house prices dataset (I have preprocessed to remove nans from the training dataset, and did one-hot encoding on cate…
-
It would be worth having something generic for all things related to stochastic approximations, to be separated from variational inference itself. E.g., a sgd class to have different stochastic gradie…
-
# Project downloaded 05.10.23, 14:00
### Bugs
- File mnist_loader.py tries to find the data with /src/training_data/... and threw an error for me atleast. Changed it to ./training_data/... and i…
-
-
#### Issue Description
Hi there!
I use a Neural Network for Deep Q Learning. After training it gives me the same outputs for every input.
My Input is an array with a size of 72 in which are eit…
-
I did not quite understand the tasks and meta mechanism used in the paper, with the replies of the author, I got a clearer view. The conclusion and discussion will be listed below to help more people.…
-
 algorithm to Torch.Optim.
### Motivation
Levenberg-Marquardt (LM), also known as damped least squares, is u…
-
In the README, it says the following about the Picard settings:
```
ortho=False, extended=False: same solution as Infomax
ortho=False, extended=True: same solution as extended-Infomax
ortho=True…
-
A specialized version of `mapAccumWhile` that keeps folding as long as the function argument returns 'Right'
```
foldWhile :: (Monad m) => (a -> s -> Either s s) -> s -> C.ConduitT a o m s
foldWh…