Ehud Ben-Reuven

1. nyTrain should be renamed to yTrain because it is the matrix itself not its size (same for nxTrain) 2. the notebook is using the inefficient loss categorical_crossentropy which needs...

you are welcomed to do the changes and send a PR

Yes it runs on CPU, especially if you already have a model and just want to do predictions. But I think you will save on your electricity bill by renting...

go to "Community AMIs and search for CUDA

https://console.aws.amazon.com/ec2/v2/home?region=us-east-1#LaunchInstanceWizard:

The avoid parameter is not very useful so I suggest to ignore it and always pass None. The idea behind it was to force the sample generator to generate something...

If you look at cell [35] of https://github.com/udibr/headlines/blob/master/predict.ipynb you will see that the `weights` shape is (944, 40000) however your error message said (40000,100) which happens to be the shape...

Ok what happened is that calling `load_weights` failed at the first layer (it should fail at the last layer) and you got as a return value the weights of the...

The '^' is just used for display to indicate that a word is not in the vocabulary used for modeling There is also an "external" vocabulary `word2idx` which includes all...

start from buzzfeed.com/archive/ huffingtonpost.com/archive/2005-5-1 . For gawker, gizmodo, deadspin use a project on github called kinja; for each of these sites start from /sitemap.xml