A challenging problem in many modern machine learning tasks is to process weight-space features, ie, to transform or extract information from the weights and gradients of a neural …
F Ballerini, PZ Ramirez, R Mirabella… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract Neural Radiance Fields (NeRFs) have emerged as a standard framework for representing 3D scenes and objects introducing a novel data type for information exchange …
PZ Ramirez, L De Luigi, D Sirocchi… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
In recent years, Neural Fields (NF s) have emerged as an effective tool for encoding diverse continuous signals such as images, videos, audio, and 3D shapes. When applied to 3D …
Permutation symmetries of deep networks make simple operations like model averaging and similarity estimation challenging. In many cases, aligning the weights of the networks …
Learning in deep weight spaces (DWS), where neural networks process the weights of other neural networks, is an emerging research direction, with applications to 2D and 3D neural …
In recent years, Neural Fields (NFs) have emerged as an effective tool for encoding diverse continuous signals such as images, videos, audio, and 3D shapes. When applied to 3D …
Neural networks efficiently encode learned information within their parameters. Consequently, many tasks can be unified by treating neural networks themselves as input …
Learning in weight spaces, where neural networks process the weights of other deep neural networks, has emerged as a promising research direction with applications in various fields …
S Zhao, Q Fan, Q Dong, Z Xing, X Yang, X He - Neurocomputing, 2024 - Elsevier
In this paper, a new variant of convolutional neural network (CNN) based on L 1 regularization is proposed. The main consideration is to generate a sparse weight matrix, ie …