riccardo/phd-thesis
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Adjustments to intros and conclusions

Browse Source 
Signed-off-by: Riccardo Finotello <riccardo.finotello@gmail.com>
This commit is contained in:
Riccardo
2020-10-13 17:48:21 +02:00
parent 295fe19683
commit 43a73d6beb
13 changed files with 260 additions and 249 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
sec/part3/conclusion.tex
View File

@@ -1,5 +1,5 @@
We have proved how a proper data analysis can lead to improvements in predictions of Hodge numbers \hodge{1}{1} and \hodge{2}{1} for \cicy $3$-folds.
Moreover considering more complex neural networks inspired by the computer vision applications~\cite{Szegedy:2015:GoingDeeperConvolutions, Szegedy:2016:RethinkingInceptionArchitecture, Szegedy:2016:Inceptionv4InceptionresnetImpact} allowed us to reach close to \SI{100}{\percent} accuracy for \hodge{1}{1} with much less data and less parameters than in previous works.
We have proved that a proper data analysis can lead to improvements in predictions of Hodge numbers \hodge{1}{1} and \hodge{2}{1} for \cicy $3$-folds.
Moreover more complex neural networks inspired by computer vision applications~\cite{Szegedy:2015:GoingDeeperConvolutions, Szegedy:2016:RethinkingInceptionArchitecture, Szegedy:2016:Inceptionv4InceptionresnetImpact} allowed us to reach close to \SI{100}{\percent} accuracy for \hodge{1}{1} with much less data and less parameters than in previous works.
While our analysis improved the accuracy for \hodge{2}{1} over what can be expected from a simple sequential neural network, we barely reached \SI{50}{\percent}.
Hence it would be interesting to push further our study to improve the accuracy.
Possible solutions would be to use a deeper Inception network, find a better architecture including engineered features, and refine the ensembling.
@@ -12,8 +12,8 @@ Or on the contrary one could generate more matrices for the same manifold in ord
Another possibility is to use the graph representation of the configuration matrix to which is automatically invariant under permutations~\cite{Hubsch:1992:CalabiyauManifoldsBestiary} (another graph representation has been decisive in~\cite{Krippendorf:2020:DetectingSymmetriesNeural} to get a good accuracy).
Techniques such as (variational) autoencoders~\cite{Kingma:2014:AutoEncodingVariationalBayes, Rezende:2014:StochasticBackpropagationApproximate, Salimans:2015:MarkovChainMonte}, cycle GAN~\cite{Zhu:2017:UnpairedImagetoimageTranslation}, invertible neural networks~\cite{Ardizzone:2019:AnalyzingInverseProblems}, graph neural networks~\cite{Gori:2005:NewModelLearning, Scarselli:2004:GraphicalbasedLearningEnvironments} or more generally techniques from geometric deep learning~\cite{Monti:2017:GeometricDeepLearning} could be helpful.
Finally, our techniques apply directly to \cicy $4$-folds~\cite{Gray:2013:AllCompleteIntersection, Gray:2014:TopologicalInvariantsFibration}.
However there are much more manifolds in this case, such that one can expect to reach a better accuracy for the different Hodge numbers (the different learning curves for the $3$-folds indicate that the model training would benefit from more data).
Finally our techniques apply directly to \cicy $4$-folds~\cite{Gray:2013:AllCompleteIntersection, Gray:2014:TopologicalInvariantsFibration}.
However there are many more manifolds in this case (around \num{e6}) and more Hodge numbers, such that one can expect to reach a better accuracy for the different Hodge numbers (the different learning curves for the $3$-folds indicate that the model training would benefit from more data).
Another interesting class of manifolds to explore with our techniques are generalized \cicy $3$-folds~\cite{Anderson:2016:NewConstructionCalabiYau}.
These and others will indeed be ground for future investigations.