🤖 machine learning
Randomly initialized autoencoders: fixed points and edge-of-chaos
This paper introduces local and global edge-of-chaos concepts for randomly initialized autoencoders to characterize the existence, stability, and basins of attraction of their fixed points using spectral techniques from Random Matrix Theory and the Sudakov-Fernique inequality.
Original paper licensed under CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). This is an AI-generated explanation of the paper below. It is not written or endorsed by the authors. For technical accuracy, refer to the original paper. Read full disclaimer
Drowning in papers in your field?
Get daily digests of the most novel papers matching your research keywords — with technical summaries, in your language.