Dataset Information

Machine learning in spectral domain.

ABSTRACT: Deep neural networks are usually trained in the space of the nodes, by adjusting the weights of existing links via suitable optimization protocols. We here propose a radically new approach which anchors the learning process to reciprocal space. Specifically, the training acts on the spectral domain and seeks to modify the eigenvalues and eigenvectors of transfer operators in direct space. The proposed method is ductile and can be tailored to return either linear or non-linear classifiers. Adjusting the eigenvalues, when freezing the eigenvectors entries, yields performances that are superior to those attained with standard methods restricted to operate with an identical number of free parameters. To recover a feed-forward architecture in direct space, we have postulated a nested indentation of the eigenvectors. Different non-orthogonal basis could be employed to export the spectral learning to other frameworks, as e.g. reservoir computing.

SUBMITTER: Giambagli L

PROVIDER: S-EPMC7910623 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning in spectral domain.

Giambagli Lorenzo L Buffoni Lorenzo L Carletti Timoteo T Nocentini Walter W Fanelli Duccio D

Nature communications 20210226 1

Deep neural networks are usually trained in the space of the nodes, by adjusting the weights of existing links via suitable optimization protocols. We here propose a radically new approach which anchors the learning process to reciprocal space. Specifically, the training acts on the spectral domain and seeks to modify the eigenvalues and eigenvectors of transfer operators in direct space. The proposed method is ductile and can be tailored to return either linear or non-linear classifiers. Adjust ...[more]

PMID: 33637729

Similar Datasets

Project description:Highlights • Trained on 80% data and tested on the remaining 20% data of 3262 impacts from 6 different impact types, a random forest kinematics classifier reached a median accuracy of 96% over 1000 random dataset partitions.• By interpreting the important classification features, the spectral characteristics of various head impact types are investigated.• With the classifier, type-specific nearest-neighbor regression models were developed for 3 injury risk metrics: 95th percentile maximum principal strain, 95th percentile maximum principal strain in corpus callosum, and cumulative strain damage. These type-specific models with classification showed higher R2 values than the baseline model without subtyping. Background Traumatic brain injury can be caused by head impacts, but many brain injury risk estimation models are not equally accurate across the variety of impacts that patients may undergo, and the characteristics of different types of impacts are not well studied. We investigated the spectral characteristics of different head impact types with kinematics classification. Methods Data were analyzed from 3262 head impacts from lab reconstruction, American football, mixed martial arts, and publicly available car crash data. A random forest classifier with spectral densities of linear acceleration and angular velocity was built to classify head impact types (e.g., football, car crash, mixed martial arts). To test the classifier robustness, another 271 lab-reconstructed impacts were obtained from 5 other instrumented mouthguards. Finally, with the classifier, type-specific, nearest-neighbor regression models were built for brain strain. Results The classifier reached a median accuracy of 96% over 1000 random partitions of training and test sets. The most important features in the classification included both low- and high-frequency features, both linear acceleration features and angular velocity features. Different head impact types had different distributions of spectral densities in low- and high-frequency ranges (e.g., the spectral densities of mixed martial arts impacts were higher in the high-frequency range than in the low-frequency range). The type-specific regression showed a generally higher R2 value than baseline models without classification. Conclusion The machine-learning-based classifier enables a better understanding of the impact kinematics spectral density in different sports, and it can be applied to evaluate the quality of impact-simulation systems and on-field data augmentation. Graphical Abstract Image, graphical abstract

Dataset Information

Machine learning in spectral domain.

Publications

Machine learning in spectral domain.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets