Summary of Pita: Physics-informed Trajectory Autoencoder, by Johannes Fischer et al.
PITA: Physics-Informed Trajectory Autoencoderby Johannes Fischer, Kevin Rösch, Martin Lauer, Christoph StillerFirst submitted to arxiv…
PITA: Physics-Informed Trajectory Autoencoderby Johannes Fischer, Kevin Rösch, Martin Lauer, Christoph StillerFirst submitted to arxiv…
InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learningby Zhe Huang, Xiaowei Yu,…
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistencyby Soumyadeep Pal, Yuguang Yao,…
SurvRNC: Learning Ordered Representations for Survival Prediction using Rank-N-Contrastby Numan Saeed, Muhammad Ridzuan, Fadillah Adamsyah…
Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detectionby Rui…
When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?by…
Reduced Jeffries-Matusita distance: A Novel Loss Function to Improve Generalization Performance of Deep Classification Modelsby…
The Effect of Different Optimization Strategies to Physics-Constrained Deep Learning for Soil Moisture Estimationby Jianxin…
Imbalance-aware Presence-only Loss Function for Species Distribution Modelingby Robin Zbinden, Nina van Tiel, Marc Rußwurm,…
A representation-learning game for classes of prediction tasksby Neria Uzan, Nir WeinbergerFirst submitted to arxiv…