TastyPancakes/Flux.jl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

clarity

Browse Source
This commit is contained in:
Mike J Innes 2017-10-16 08:59:30 +01:00
parent 83cc77c860
commit 32c8698869
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/src/models/recurrence.md
View File

@ -25,7 +25,7 @@ Information stored in `h` is preserved for the next prediction, allowing it to f
(This might be important if, for example, each `x` represents one word of a sentence; the model's interpretation of the word "bank" should change if the previous input was "river" rather than "investment".) (This might be important if, for example, each `x` represents one word of a sentence; the model's interpretation of the word "bank" should change if the previous input was "river" rather than "investment".)
Flux's RNN support closely follows this mathematical perspective. The most basic RNN is as close as possible to a standard `Dense` layer, and the output and hidden state are the same. By convention, the hidden state is the first input and output. Flux's RNN support closely follows this mathematical perspective. The most basic RNN is as close as possible to a standard `Dense` layer, and the output is also the hidden state.
```julia ```julia
Wxh = randn(5, 10) Wxh = randn(5, 10)