Autoencoder Neural Networks - Data-Driven Dynamics | Lecture 23 скачать в хорошем качестве

Autoencoder Neural Networks - Data-Driven Dynamics | Lecture 23

In this lecture, we introduce a powerful new neural network architecture inspired by autoencoders. We show how, when trained correctly, autoencoders can mimic a topological conjugacy, effectively capturing the underlying structure between two dynamical systems. We outline the fundamentals of the network architecture and provide a hands-on demonstration by finding the conjugacy between the tent map and the logistic map from the previous lecture. This approach highlights how modern machine learning can uncover deep connections in dynamical systems that are otherwise difficult to compute by hand. Jupyter notebook comes from Tent2Logistic.ipynb here: https://github.com/jbramburger/DataDr... PyTorch version: https://github.com/jbramburger/DataDr... Get the book here: https://epubs.siam.org/doi/10.1137/1.... Scripts and notebooks to reproduce all examples: https://github.com/jbramburger/DataDr... This book provides readers with: methods not found in other texts as well as novel ones developed just for this book; an example-driven presentation that provides background material and descriptions of methods without getting bogged down in technicalities; examples that demonstrate the applicability of a method and introduce the features and drawbacks of their application; and a code repository in the online supplementary material that can be used to reproduce every example and that can be repurposed to fit a variety of applications not found in the book. More information on the instructor: https://hybrid.concordia.ca/jbrambur/ Follow @jbramburger7 on Twitter for updates.