Sloppy Models, Differential Geometry, and Why Science Works
Offered By: Santa Fe Institute via YouTube
Course Description
Overview
Syllabus
Intro
Sloppy Models, Differential geometry, and why science works
Emergent vs. Fundamental Reducing the number of basic parameters Physics Controlled
Systems Biology: Cell Protein Reactions
Sloppy 'Universality'
Fisher Information is the Metric Fisher Information Matrix (FIM) measures distance
Physics: Sloppiness and Emergence Ben Machta, Ricky Chachra, Mark Transtrum
The Model Manifold: Predictions Two exponentials ..
The Model Manifold is a Hyperribbon Mark Transtrum, Ben Machta
Rigorous hyperellipsoid bounds on model manifold
Why a hyperribbon?
Hyperribbons for Ising: Curing the curse of dimensionality
MBAM Generation of Reduced Models
Sloppy Models, Differential geometry, and the space of model predictions
Taught by
Santa Fe Institute
Tags
Related Courses
Sparse Representations in Signal and Image Processing: FundamentalsTechnion - Israel Institute of Technology via edX Filters and Other Potions for Early Vision and Recognition
MITCBMM via YouTube ADSI Summer Workshop- Algorithmic Foundations of Learning and Control, Pablo Parrilo
Paul G. Allen School via YouTube A Function Space View of Overparameterized Neural Networks - Rebecca Willet, University of Chicago
Alan Turing Institute via YouTube Approximation with Deep Networks - Remi Gribonval, Inria
Alan Turing Institute via YouTube