notxia/unibo-ai-notes
1
0
Fork 0
mirror of https://github.com/NotXia/unibo-ai-notes.git synced 2025-12-15 19:12:22 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1 from liuktc/patch-1

Browse Source 
Update _rnn.tex
This commit is contained in:
Tian Cheng (Riccardo) Xia
2024-10-27 17:38:37 +01:00
committed by GitHub
parent cff26da369 9e8675ab9d
commit 606151025c
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/year2/natural-language-processing/sections/_rnn.tex
View File

@ -39,7 +39,7 @@
\begin{description} \begin{description}
\item[Training] \item[Training]
Given the predicted distribution $\hat{\vec{y}}^{(t)}$ and ground-truth $\vec{y}^{(t)}$ at step $t$, the loss is computed as the cross-entropy: Given the predicted distribution $\hat{\vec{y}}^{(t)}$ and ground-truth $\vec{y}^{(t)}$ at step $t$, the loss is computed as the cross-entropy:
\[ \mathcal{L}^{(t)}(\matr{\theta}) = - \sum_{v \in V} \vec{y}_v^{(t)} \log\left( \hat{\vec{y}}_w^{(t)} \right) \] \[ \mathcal{L}^{(t)}(\matr{\theta}) = - \sum_{v \in V} \vec{y}_v^{(t)} \log\left( \hat{\vec{y}}_v^{(t)} \right) \]
\begin{description} \begin{description}
\item[Teacher forcing] \marginnote{Teacher forcing} \item[Teacher forcing] \marginnote{Teacher forcing}
@ -68,4 +68,4 @@
\item[Greedy] Select the token with the highest probability. \item[Greedy] Select the token with the highest probability.
\item[Sampling] Randomly sample the token following the probabilities of the output distribution. \item[Sampling] Randomly sample the token following the probabilities of the output distribution.
\end{descriptionlist} \end{descriptionlist}
\end{description} \end{description}