Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion _posts/2015-05-21-rnn-effectiveness.markdown
Original file line number Diff line number Diff line change
Expand Up @@ -324,7 +324,7 @@ static int indicate_policy(void)
}
```

The code looks really quite great overall. Of course, I don't think it compiles but when you scroll through the generate code it feels very much like a giant C code base. Notice that the RNN peppers its code with comments here and there at random. It is also very good at making very few syntactic errors. For example, it uses strings properly, pointer notation, etc. It also opens and closes brackets `{[` correctly and learns to indent its code very well. A common error is that it can't keep track of variable names: It often uses undefined variables (e.g. `rw` above), declares variables it never uses (e.g. `int error`), or returns non-existing variables. Lets see a few more examples. Here's another snippet that shows a wider array of operations that the RNN learns:
The code looks really quite great overall. Of course, I don't think it compiles but when you scroll through the generated code it feels very much like a giant C code base. Notice that the RNN peppers its code with comments here and there at random. It is also very good at making very few syntactic errors. For example, it uses strings properly, pointer notation, etc. It also opens and closes brackets `{[` correctly and learns to indent its code very well. A common error is that it can't keep track of variable names: It often uses undefined variables (e.g. `rw` above), declares variables it never uses (e.g. `int error`), or returns non-existing variables. Lets see a few more examples. Here's another snippet that shows a wider array of operations that the RNN learns:

```c
/*
Expand Down