Zobrazeno 1 - 10
of 854
pro vyhledávání: '"Ferreira, Fabio"'
Many Self-Supervised Learning (SSL) methods aim for model invariance to different image augmentations known as views. To achieve this invariance, conventional approaches make use of random sampling operations within the image augmentation pipeline. W
Externí odkaz:
http://arxiv.org/abs/2310.03940
With the ever-increasing number of pretrained models, machine learning practitioners are continuously faced with which pretrained model to use, and how to finetune it for a new dataset. In this paper, we propose a methodology that jointly searches fo
Externí odkaz:
http://arxiv.org/abs/2306.03828
Autor:
Wagner, Diane, Ferreira, Fabio, Stoll, Danny, Schirrmeister, Robin Tibor, Müller, Samuel, Hutter, Frank
Self-Supervised Learning (SSL) has become a very active area of Deep Learning research where it is heavily used as a pre-training method for classification and other tasks. However, the rapid pace of advancements in this area comes at a price: traini
Externí odkaz:
http://arxiv.org/abs/2207.07875
We study the dielectric response of few layered crystals of various transition metal dichalcogenides (TMDs) and hexagonal Boron Nitride (hBN). We showed that the out-of-plane polarizability of a multilayer crystal (which characterizes response to the
Externí odkaz:
http://arxiv.org/abs/2206.09183
Autor:
Öztürk, Ekrem, Ferreira, Fabio, Jomaa, Hadi S., Schmidt-Thieme, Lars, Grabocka, Josif, Hutter, Frank
Publikováno v:
International Conference on Machine Learning 2022
Given a new dataset D and a low compute budget, how should we choose a pre-trained model to fine-tune to D, and set the fine-tuning hyperparameters without risking overfitting, particularly if D is small? Here, we extend automated machine learning (A
Externí odkaz:
http://arxiv.org/abs/2206.08476
Autor:
Baz, Adrian El, Ullah, Ihsan, Alcobaça, Edesio, Carvalho, André C. P. L. F., Chen, Hong, Ferreira, Fabio, Gouk, Henry, Guan, Chaoyu, Guyon, Isabelle, Hospedales, Timothy, Hu, Shell, Huisman, Mike, Hutter, Frank, Liu, Zhengying, Mohr, Felix, Öztürk, Ekrem, van Rijn, Jan N., Sun, Haozhe, Wang, Xin, Zhu, Wenwu
Publikováno v:
NeurIPS 2021 Competition and Demonstration Track, Dec 2021, On-line, United States
Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such resources are avai
Externí odkaz:
http://arxiv.org/abs/2206.08138
Publikováno v:
International Conference on Learning Representations (ICLR 2022)
We introduce Synthetic Environments (SEs) and Reward Networks (RNs), represented by neural networks, as proxy environment models for training Reinforcement Learning (RL) agents. We show that an agent, after being trained exclusively on the SE, is abl
Externí odkaz:
http://arxiv.org/abs/2202.02790
Autor:
Liu, Zhengying, Pavao, Adrien, Xu, Zhen, Escalera, Sergio, Ferreira, Fabio, Guyon, Isabelle, Hong, Sirui, Hutter, Frank, Ji, Rongrong, Junior, Julio C. S. Jacques, Li, Ge, Lindauer, Marius, Luo, Zhipeng, Madadi, Meysam, Nierhoff, Thomas, Niu, Kangning, Pan, Chunguang, Stoll, Danny, Treguer, Sebastien, Wang, Jin, Wang, Peng, Wu, Chenglin, Xiong, Youcheng, Zela, Arbe r, Zhang, Yang
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI) 2021
This paper reports the results and post-challenge analyses of ChaLearn's AutoDL challenge series, which helped sorting out a profusion of AutoML solutions for Deep Learning (DL) that had been introduced in a variety of settings, but lacked fair compa
Externí odkaz:
http://arxiv.org/abs/2201.03801
Publikováno v:
In Building and Environment 15 August 2024 262
Autor:
Figueiredo, Nuno M., Mateus, Pedro, Ponte, Filipa, Sharma, Pooja, Ferreira, Jorge, Cavaleiro, Diogo, Deuermeier, Jonas, Ferreira, Fábio, Cavaleiro, Albano, Carvalho, Sandra
Publikováno v:
In Vacuum August 2024 226