Site is currently under maintenance
Some features may be unavailable or limited during this time. We apologize for any inconvenience and appreciate your patience.

Automated Author Profile

Tohouri, Pascal

Current S-Index

7.8

Sum of Dataset Indices for all datasets

Average Dataset Index per Dataset

0.6

Average Dataset Index per dataset

Total Datasets

13

Total datasets for this author

Average FAIR Score

24.1%

Average FAIR Score per dataset

Total Citations

0

Total citations to the author's datasets

Total Mentions

0

Total mentions of the author's datasets

S-Index Interpretation

S-Index Over Time

Cumulative Citations Over Time

Cumulative Mentions Over Time

Datasets

Training 3D Spatially Embedded Neural Networks for Regression via Gradient Descent

This study examines a feed-forward neural network embedded in Euclidean R3 space. Nuclei coordinates condition network parameters. Backpropagating from loss-parameter to loss-coordinate derivatives enables spatially-embedded gradient descent. A dense multi-layer perceptron (MLP) learns price-prediction on the California Housing dataset. The model demonstrates performance comparable to conventional, non-spatial MLP predictions. Robustness examinations via re-initialisation sensitivity tests, and spatial analysis via node ablation and activation imaging, reveal complexity and interpretability characteristics unique to the spatially embedded model.

Authors

  • Tohouri, Pascal
0 Citations0 Mentions81% FAIR2.0 Dataset Index
10.6084/m9.figshare.29588804.v1January 2025

Training 3D Spatially Embedded Neural Networks for Regression via Gradient Descent

This study examines a feed-forward neural network embedded in Euclidean R3 space. Nuclei coordinates condition network parameters. Backpropagating from loss-parameter to loss-coordinate derivatives enables spatially-embedded gradient descent. A dense multi-layer perceptron (MLP) learns price-prediction on the California Housing dataset. The model demonstrates performance comparable to conventional, non-spatial MLP predictions. Robustness examinations via re-initialisation sensitivity tests, and spatial analysis via node ablation and activation imaging, reveal complexity and interpretability characteristics unique to the spatially embedded model.

Authors

  • Tohouri, Pascal
0 Citations0 Mentions13% FAIR0.3 Dataset Index
10.6084/m9.figshare.29588804.v2January 2025

Training 3D Spatially Embedded Neural Networks for Regression via Gradient Descent

This study examines a feed-forward neural network embedded in Euclidean R3 space. Nuclei coordinates condition network parameters. Backpropagating from loss-parameter to loss-coordinate derivatives enables spatially-embedded gradient descent. A dense multi-layer perceptron (MLP) learns price-prediction on the California Housing dataset. The model demonstrates performance comparable to conventional, non-spatial MLP predictions. Robustness examinations via re-initialisation sensitivity tests, and spatial analysis via node ablation and activation imaging, reveal complexity and interpretability characteristics unique to the spatially embedded model.

Authors

  • Tohouri, Pascal
0 Citations0 Mentions13% FAIR0.3 Dataset Index
10.6084/m9.figshare.29588804.v3January 2025

Training 3D Spatially Embedded Neural Networks for Regression via Gradient Descent

This study examines a feed-forward neural network embedded in Euclidean R3 space. Nuclei coordinates condition network parameters. Backpropagating from loss-parameter to loss-coordinate derivatives enables spatially-embedded gradient descent. A dense multi-layer perceptron (MLP) learns price-prediction on the California Housing dataset. The model demonstrates performance comparable to conventional, non-spatial MLP predictions. Robustness examinations via re-initialisation sensitivity tests, and spatial analysis via node ablation and activation imaging, reveal complexity and interpretability characteristics unique to the spatially embedded model.

Authors

  • Tohouri, Pascal
0 Citations0 Mentions13% FAIR0.3 Dataset Index
10.6084/m9.figshare.29588804.v4January 2025

Training 3D Spatially Embedded Neural Networks for Regression via Gradient Descent

This study examines a feed-forward neural network embedded in Euclidean R3 space. Nuclei coordinates condition network parameters. Backpropagating from loss-parameter to loss-coordinate derivatives enables spatially-embedded gradient descent. A dense multi-layer perceptron (MLP) learns price-prediction on the California Housing dataset. The model demonstrates performance comparable to conventional, non-spatial MLP predictions. Robustness examinations via re-initialisation sensitivity tests, and spatial analysis via node ablation and activation imaging, reveal complexity and interpretability characteristics unique to the spatially embedded model.

Authors

  • Tohouri, Pascal
0 Citations0 Mentions81% FAIR2.0 Dataset Index
10.6084/m9.figshare.29588804.v5January 2025

Training 3D Spatially Embedded Neural Networks for Regression via Gradient Descent

This study examines a feed-forward neural network embedded in Euclidean R3 space. Nuclei coordinates condition network parameters. Backpropagating from loss-parameter to loss-coordinate derivatives enables spatially-embedded gradient descent. A dense multi-layer perceptron (MLP) learns price-prediction on the California Housing dataset. The model demonstrates performance comparable to conventional, non-spatial MLP predictions. Robustness examinations via re-initialisation sensitivity tests, and spatial analysis via node ablation and activation imaging, reveal complexity and interpretability characteristics unique to the spatially embedded model.

Authors

  • Tohouri, Pascal
0 Citations0 Mentions13% FAIR0.3 Dataset Index
10.6084/m9.figshare.29588804.v6January 2025

Training 3D Spatially Embedded Neural Networks for Regression via Gradient Descent

This study examines a feed-forward neural network embedded in Euclidean R3 space. Nuclei coordinates condition network parameters. Backpropagating from loss-parameter to loss-coordinate derivatives enables spatially-embedded gradient descent. A dense multi-layer perceptron (MLP) learns price-prediction on the California Housing dataset. The model demonstrates performance comparable to conventional, non-spatial MLP predictions. Robustness examinations via re-initialisation sensitivity tests, and spatial analysis via node ablation and activation imaging, reveal complexity and interpretability characteristics unique to the spatially embedded model.

Authors

  • Tohouri, Pascal
0 Citations0 Mentions15% FAIR0.4 Dataset Index
10.6084/m9.figshare.29588804.v7January 2025

Training 3D Spatially Embedded Neural Networks for Regression via Gradient Descent

This study examines a feed-forward neural network embedded in Euclidean R3 space. Nuclei coordinates condition network parameters. Backpropagating from loss-parameter to loss-coordinate derivatives enables spatially-embedded gradient descent. A dense multi-layer perceptron (MLP) learns price-prediction on the California Housing dataset. The model demonstrates performance comparable to conventional, non-spatial MLP predictions. Robustness examinations via re-initialisation sensitivity tests, and spatial analysis via node ablation and activation imaging, reveal complexity and interpretability characteristics unique to the spatially embedded model.

Authors

  • Tohouri, Pascal
0 Citations0 Mentions13% FAIR0.3 Dataset Index
10.6084/m9.figshare.29588804.v8January 2025

Training 3D Spatially Embedded Neural Networks for Regression via Gradient Descent

This study examines a feed-forward neural network embedded in Euclidean R3 space. Nuclei coordinates condition network parameters. Backpropagating from loss-parameter to loss-coordinate derivatives enables spatially-embedded gradient descent. A dense multi-layer perceptron (MLP) learns price-prediction on the California Housing dataset. The model demonstrates performance comparable to conventional, non-spatial MLP predictions. Robustness examinations via re-initialisation sensitivity tests, and spatial analysis via node ablation and activation imaging, reveal complexity and interpretability characteristics unique to the spatially embedded model.

Authors

  • Tohouri, Pascal
0 Citations0 Mentions13% FAIR0.3 Dataset Index
10.6084/m9.figshare.29588804.v9January 2025

Training 3D Spatially Embedded Neural Networks for Regression via Gradient Descent

This study examines a feed-forward neural network embedded in Euclidean R3 space. Nuclei coordinates condition network parameters. Backpropagating from loss-parameter to loss-coordinate derivatives enables spatially-embedded gradient descent. A dense multi-layer perceptron (MLP) learns price-prediction on the California Housing dataset. The model demonstrates performance comparable to conventional, non-spatial MLP predictions. Robustness examinations via re-initialisation sensitivity tests, and spatial analysis via node ablation and activation imaging, reveal complexity and interpretability characteristics unique to the spatially embedded model.

Authors

  • Tohouri, Pascal
0 Citations0 Mentions13% FAIR0.3 Dataset Index
10.6084/m9.figshare.29588804.v10January 2025