Scatter Plot from Scientific Research

CC-BY
633
Views
0
Likes
Citation
Test performance of each model for selected computational tasks (N = 350 models, except for the autoencoder with n = 295) with respect to the number of layers. Appropriate metrics are shown per task (regression: mean squared error; classification: accuracy; autoencoder: relative error per muscle length; redundancy reduction task: Barlow loss). Neural network architectures were designed to integrate proprioceptive signals in different ways: spatial-temporal, temporal-spatial, spatiotemporal TCNs, and spatial-LSTM. SeeFigure S1for more tasks.
#Scatter Plot#Test Performance#Computational Tasks#Neural Network Architectures#Proprioceptive Signals#Regression#Classification#Autoencoder#Redundancy Reduction
Related Plots
Browse by Category
Popular Collections
Discover More Scientific Plots
Browse thousands of high-quality scientific visualizations from open-access research