Search Results for author:
Found 2 papers, 0 papers with code
Automatic laminectomy cutting plane planning based on artificial intelligence in robot assisted laminectomy surgery
Results: In the first stage, the average localization error of the SPU-Net algorithm for the seven key points was 0. 65mm.
Deep Model Fusion: A Survey
Specifically, we categorize existing deep model fusion methods as four-fold: (1) "Mode connectivity", which connects the solutions in weight space via a path of non-increasing loss, in order to obtain better initialization for model fusion; (2) "Alignment" matches units between neural networks to create better conditions for fusion; (3) "Weight average", a classical model fusion method, averages the weights of multiple models to obtain more accurate results closer to the optimal solution; (4) "Ensemble learning" combines the outputs of diverse models, which is a foundational technique for improving the accuracy and robustness of the final model.
