Zobrazeno 1 - 10
of 2 303
pro vyhledávání: '"Moura José"'
Foundation models are now a major focus of leading technology organizations due to their ability to generalize across diverse tasks. Existing approaches for adapting foundation models to new applications often rely on Federated Learning (FL) and disc
Externí odkaz:
http://arxiv.org/abs/2410.18352
Calculus of Variations is the mathematics of functional optimization, i.e., when the solutions are functions over a time interval. This is particularly important when the time interval is unknown like in minimum-time control problems, so that forward
Externí odkaz:
http://arxiv.org/abs/2410.06277
Peer-to-peer learning is an increasingly popular framework that enables beyond-5G distributed edge devices to collaboratively train deep neural networks in a privacy-preserving manner without the aid of a central server. Neural network training algor
Externí odkaz:
http://arxiv.org/abs/2409.15267
Autor:
Neo, Giseldo da Silva, Moura, José Antão Beltrão, de Almeida, Hyggo Oliveira, Neo, Alana Viana Borges da Silva, Júnior, Olival de Gusmão Freitas
Publikováno v:
Proceedings of the 16th International Conference on Computer Supported Education (CSEDU), Volume 2, 2024, 51-62
User Stories record what must be built in projects that use agile practices. User Stories serve both to estimate effort, generally measured in Story Points, and to plan what should be done in a Sprint. Therefore, it is essential to train software eng
Externí odkaz:
http://arxiv.org/abs/2406.16259
Directly parameterizing and learning gradients of functions has widespread significance, with specific applications in inverse problems, generative modeling, and optimal transport. This paper introduces gradient networks (GradNets): novel neural netw
Externí odkaz:
http://arxiv.org/abs/2404.07361
Uncertainty quantification of neural networks is critical to measuring the reliability and robustness of deep learning systems. However, this often involves costly or inaccurate sampling methods and approximations. This paper presents a sample-free m
Externí odkaz:
http://arxiv.org/abs/2403.16163
Autor:
Pranav, Srinivasa, Moura, José M. F.
Peer-to-peer deep learning algorithms are enabling distributed edge devices to collaboratively train deep neural networks without exchanging raw training data or relying on a central server. Peer-to-Peer Learning (P2PL) and other algorithms based on
Externí odkaz:
http://arxiv.org/abs/2312.13602
In a Networked Dynamical System (NDS), each node is a system whose dynamics are coupled with the dynamics of neighboring nodes. The global dynamics naturally builds on this network of couplings and it is often excited by a noise input with nontrivial
Externí odkaz:
http://arxiv.org/abs/2312.11324
While deep learning has been very successful in computer vision, real world operating conditions such as lighting variation, background clutter, or occlusion hinder its accuracy across several tasks. Prior work has shown that hybrid models -- combini
Externí odkaz:
http://arxiv.org/abs/2312.08650
Learning the Causal Structure of Networked Dynamical Systems under Latent Nodes and Structured Noise
This paper considers learning the hidden causal network of a linear networked dynamical system (NDS) from the time series data at some of its nodes -- partial observability. The dynamics of the NDS are driven by colored noise that generates spurious
Externí odkaz:
http://arxiv.org/abs/2312.05974