The GRU is a lighter alternative to the LSTM, with two gates and no separate cell state. With input , previous state , of shape (D, 3H), of shape (H, 3H) and of shape (3H,), split into r, z, n parts in that order:
Unlock this and every premium problem across all tracks — plus hidden-test grading, advanced AI engineering modules and new content every week.
Start 7-day free trial