Sequence Models

https://d2l.ai/chapter_recurrent-neural-networks/sequence.html

In section 8.1.1.1

This leads to models that estimate x_t with \hat{x}_t = P(x_t \mid h_{t})

But going by the figure 8.1.2, isn’t x^_t calculated through a combination of h_t and x_t-1?

\hat{x}_t is calculated based on h_t, where β„Ž_𝑑=𝑔(β„Ž_{π‘‘βˆ’1},π‘₯_{π‘‘βˆ’1})