Deep Learning-based Analysis of Basins of Attraction
This research addresses the challenge of characterizing the complexity and unpredictability of basins within various dynamical systems. The main focus is on demonstrating the efficiency of convolutional neural networks (CNNs) in this field. Conventional methods become computationally demanding when analyzing multiple basins of attraction across different parameters of dynamical systems. Our research presents an innovative approach that employs CNN architectures for this purpose, showcasing their superior performance in comparison to conventional methods. We conduct a comparative analysis of various CNN models, highlighting the effectiveness of our proposed characterization method while acknowledging the validity of prior approaches. The findings not only showcase the potential of CNNs but also emphasize their significance in advancing the exploration of diverse behaviors within dynamical systems.
Code (1)
Tasks
Deep LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Visualising Basins of Attraction for the Cross-Entropy and the Squared Error Neural Network Loss Functions
Quantification of the stationary points and the associated basins of attraction of neural network loss surfaces is an important step towards a better understanding of neural network loss surfaces at large. This work prop…
Topological properties of basins of attraction and expressiveness of width bounded neural networks
In Radhakrishnan et al. [2020], the authors empirically show that autoencoders trained with usual SGD methods shape out basins of attraction around their training data. We consider network functions of width not exceedin…
Critical Slowing Down along the Separatrix of Lotka-Volterra Model of Competition
The Lotka-Volterra model of competition has been studied by numerical simulations using the Runge-Kutta-Fehlberg algorithm. The stable fixed points, unstable fixed point, saddle node, basins of attraction, and the separa…
Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data
When do language diffusion models memorize their training data, and how to quantitatively assess their true generative regime? We address these questions by showing that Uniform-based Discrete Diffusion Models (UDDMs) fu…
Riddled basin geometry sets fundamental limits to predictability and reproducibility in deep learning
Fundamental limits to predictability are central to our understanding of many physical and computational systems. Here we show that, despite its remarkable capabilities, deep learning exhibits such fundamental limits roo…