Skip to content

Conversation

@coffeedjimmy
Copy link

In the tutorial notebook, I found one curious point.

In the forward propagation, s[-1] is added as the additional operation. However, in the declaration of s array, it is defined as (T+1, hidden_dim) shape.

I know this is very minor point but when I study RNN with your post I took some time why this is (T+1, hidden_dim) instead of (T, hidden_dim). Due to this, I send this PR.

Thank you for your posting again.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant