will-do.tex 1.0 KB

123456789101112131415161718192021222324
  1. \subsection{What will I do next?}
  2. \begin{frame}{What will I do next?}
  3. \begin{itemize}
  4. \item Include the currently best model in write-math.com
  5. \item Evaluate preprocessing steps
  6. \item Try other features
  7. \item Try other topologies / trainings (e.g. pretraining, newbob)
  8. \item Eventually try convolutional neural nets
  9. \end{itemize}
  10. \end{frame}
  11. % \subsection{Far future}
  12. % \begin{frame}{What could be done?}
  13. % \begin{itemize}
  14. % \item Make use of audio data in a multimodal approach\\
  15. % e.g. $R$ and $\mathcal{R}$
  16. % \item Currently, the Lecture Translation system doesn't recognize math.\\
  17. % You get \enquote{integral of e raised to the power of x d x} instead
  18. % of $\int e^x \mathrm{d} x$.
  19. % \item Spoken math is ambigous: $\sqrt{a+b}$ vs. $\sqrt{a} + b$
  20. % \item The language model I create could help to find probable formulas
  21. % \item The platform could be used to get more input data of users
  22. % \end{itemize}
  23. % \end{frame}