Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Hounie, Ignacio"'
Low Rank Adaptation (LoRA) is a popular Parameter Efficient Fine Tuning (PEFT) method that effectively adapts large pre-trained models for downstream tasks. LoRA parameterizes model updates using low-rank matrices at each layer, significantly reducin
Externí odkaz:
http://arxiv.org/abs/2410.04060
Several applications in time series forecasting require predicting multiple steps ahead. Despite the vast amount of literature in the topic, both classical and recent deep learning based approaches have mostly focused on minimising performance averag
Externí odkaz:
http://arxiv.org/abs/2402.09373
When deploying machine learning solutions, they must satisfy multiple requirements beyond accuracy, such as fairness, robustness, or safety. These requirements are imposed during training either implicitly, using penalties, or explicitly, using const
Externí odkaz:
http://arxiv.org/abs/2306.02426
Enabling low precision implementations of deep learning models, without considerable performance degradation, is necessary in resource and latency constrained settings. Moreover, exploiting the differences in sensitivity to quantization across layers
Externí odkaz:
http://arxiv.org/abs/2210.15623
Underlying data structures, such as symmetries or invariances to transformations, are often exploited to improve the solution of learning tasks. However, embedding these properties in models or learning algorithms can be challenging and computational
Externí odkaz:
http://arxiv.org/abs/2209.15031
Autor:
Zinemanas, Pablo, Hounie, Ignacio, Cancela, Pablo, Font Corbera, Frederic, Rocamora, Martín, Serra, Xavier
Comunicació presentada a: 5th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2020) celebrat el 2 i 3 de novembre de 2020 a Tòquio, Japó. This document presents DCASE-models, an open–source Python library for rapid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1610::5a613c945d64da29b2a1ac4483ab1f0d
http://hdl.handle.net/10230/45641
http://hdl.handle.net/10230/45641
Publikováno v:
COLIBRI
Universidad de la República
instacron:Universidad de la República
Universidad de la República
instacron:Universidad de la República
We present an implementation of the PACO-DCT inpainting algorithm. This method is based on maximizing the likelihood of image patches in terms of their DCT coefficients, while requiring consensus on the overlapping patches. The resulting problem is s