News for hackers. Stuff that matters.

yolorn123

Re:Understanding LSTM and its diagrams on Wednesday November 15, 2017 @10:36PM (#15710097)
The reason is there only two gates for Gru, they don't have an internal state as that of LSTM, since having few parameters compared to LSTM it takes less time to train
Re:A New Twist on Neural Networks on Thursday November 02, 2017 @08:51AM (#15609903)
what's the difference between concatinating the layer and adding more layers?
Re:Ask HN: Which MOOCs are often overlooked? on Sunday May 21, 2017 @09:53AM (#14387306)
I'm thinking of taking the course. How is the course when compared to other mooc?