Designing machine learning architectures for processing neural networks in their raw weight
matrix form is a newly introduced research direction. Unfortunately, the unique symmetry …

Typical deep visual recognition models are capable of performing the one task they were
trained on. In this paper, we tackle the extremely difficult problem of combining completely …

In this paper we look into the conjecture of Entezari et al.(2021) which states that if the
permutation invariance of neural networks is taken into account, then there is likely no loss …

Recent work has revealed many intriguing empirical phenomena in neural network training,
despite the poorly understood and highly complex loss landscapes and training dynamics …

Federated learning aims to train models collaboratively across different clients without
sharing data for privacy considerations. However, one major challenge for this learning …

In this paper, we study multi-target domain adaptation of scene understanding models.
While previous methods achieved commendable results through inter-domain consistency …

Many algorithms and observed phenomena in deep learning appear to be affected by
parameter symmetries--transformations of neural network parameters that do not change the …

Utilization of wind energy sources provides advantages in terms of being environmentally
friendly, and it can be energy source is realible. The analysis of wind mill control using …

Objective: Deep neural network (DNN) techniques have demonstrated significant
advantages over regression and some other techniques. In recent studies, DNN-based …

Merging models becomes a fundamental procedure in some applications that consider
model efficiency and robustness. The training randomness or Non-IID data poses a huge …