Unsupervised learning methods for molecular simulation data
Unsupervised learning is becoming an essential tool to analyze the increasingly large
amounts of data produced by atomistic and molecular simulations, in material science, solid …
amounts of data produced by atomistic and molecular simulations, in material science, solid …
Collective variable-based enhanced sampling and machine learning
M Chen - The European Physical Journal B, 2021 - Springer
Collective variable-based enhanced sampling methods have been widely used to study
thermodynamic properties of complex systems. Efficiency and accuracy of these enhanced …
thermodynamic properties of complex systems. Efficiency and accuracy of these enhanced …
Dataset distillation with infinitely wide convolutional networks
The effectiveness of machine learning algorithms arises from being able to extract useful
features from large amounts of data. As model and dataset sizes increase, dataset …
features from large amounts of data. As model and dataset sizes increase, dataset …
Patch svdd: Patch-level svdd for anomaly detection and segmentation
In this paper, we address the problem of image anomaly detection and segmentation.
Anomaly detection involves making a binary decision as to whether an input image contains …
Anomaly detection involves making a binary decision as to whether an input image contains …
A universal law of robustness via isoperimetry
Classically, data interpolation with a parametrized model class is possible as long as the
number of parameters is larger than the number of equations to be satisfied. A puzzling …
number of parameters is larger than the number of equations to be satisfied. A puzzling …
Intrinsic dimension of data representations in deep neural networks
Deep neural networks progressively transform their inputs across multiple processing layers.
What are the geometrical properties of the representations learned by these networks? Here …
What are the geometrical properties of the representations learned by these networks? Here …
A universal law of robustness via isoperimetry
Classically, data interpolation with a parametrized model class is possible as long as the
number of parameters is larger than the number of equations to be satisfied. A puzzling …
number of parameters is larger than the number of equations to be satisfied. A puzzling …
Intrinsic dimension estimation for robust detection of ai-generated texts
E Tulchinskii, K Kuznetsov… - Advances in …, 2024 - proceedings.neurips.cc
Rapidly increasing quality of AI-generated content makes it difficult to distinguish between
human and AI-generated texts, which may lead to undesirable consequences for society …
human and AI-generated texts, which may lead to undesirable consequences for society …
Shallow neural networks for fluid flow reconstruction with limited sensors
NB Erichson, L Mathelin, Z Yao… - … of the Royal …, 2020 - royalsocietypublishing.org
In many applications, it is important to reconstruct a fluid flow field, or some other high-
dimensional state, from limited measurements and limited data. In this work, we propose a …
dimensional state, from limited measurements and limited data. In this work, we propose a …
Scikit-dimension: a python package for intrinsic dimension estimation
Dealing with uncertainty in applications of machine learning to real-life data critically
depends on the knowledge of intrinsic dimensionality (ID). A number of methods have been …
depends on the knowledge of intrinsic dimensionality (ID). A number of methods have been …