New answers tagged

0

(Old question, I know...) It is not that we need both an encoder and decoder for sequence-to-sequence models - this decoupling of "reading" and "generating" just works better very often. Example for Sequence-to-sequence without two RNNs To prove my point above, here is an example from machine translation. Current machine translation systems are sequence-...


2

Maybe you are looking for a combination of a version control system (like git and Github) and a tool like comet.ml. In the past, I used comet.ml to keep track of different experiments performed with different hyper-parameters or different versions of the code. There are other alternatives to comet.ml, such as sacred, but they may also have different features ...


0

GPT2 predicts the next word that people will say. https://openai.com/blog/better-language-models/ Facebook predicts what will make you keep using their site. Youtube predicts what videos you will click on.


Top 50 recent answers are included