Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2024 Aug 12;12(1):nwae279. doi: 10.1093/nsr/nwae279

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2024. Published by Oxford University Press on behalf of China Science Publishing & Media Ltd.

This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.

PMC Copyright notice

Figure 4. — The experimental results of NIS+ on learning the collective flocking behaviors of the boids model. Panels (a) and (e) present real and predicted data on boid trajectories. Concretely, they present the comparison results for multi-step predictions under the condition of two separating groups, and random deflection angles. Panel (b) showcases the escalation of MAE for multi-step predictions as the radius r, which represents the range of initial positions of boids in (a), extends beyond the limits of the training data. Panel (c) depicts the trend of changes with training epochs of NIS+ using different hyperparameters of q, which represents the scales of different macro-states. Panel (d) presents the saliency map, which visually depicts the association between each macroscopic dimension and the spatial coordinates of each boid. The interpretation can be found in Section S6.2. Panels (f) and (g) show the changes in and normalized MAE under different noise levels for (f) the extrinsic noise () and (g) intrinsic noise (). In both (f) and (g), the horizontal lines represent the threshold 0.3 for the violation of the constraint of error in Equation (1).

Inline graphic — The experimental results of NIS+ on learning the collective flocking behaviors of the boids model. Panels (a) and (e) present real and predicted data on boid trajectories. Concretely, they present the comparison results for multi-step predictions under the condition of two separating groups, and random deflection angles. Panel (b) showcases the escalation of MAE for multi-step predictions as the radius r, which represents the range of initial positions of boids in (a), extends beyond the limits of the training data. Panel (c) depicts the trend of changes with training epochs of NIS+ using different hyperparameters of q, which represents the scales of different macro-states. Panel (d) presents the saliency map, which visually depicts the association between each macroscopic dimension and the spatial coordinates of each boid. The interpretation can be found in Section S6.2. Panels (f) and (g) show the changes in and normalized MAE under different noise levels for (f) the extrinsic noise () and (g) intrinsic noise (). In both (f) and (g), the horizontal lines represent the threshold 0.3 for the violation of the constraint of error in Equation (1).