Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Argerich, Luis"'
Publikováno v:
Long version of the paper of ACM-SAC 2024
Machine learning models typically focus on specific targets like creating classifiers, often based on known population feature distributions in a business context. However, models calculating individual features adapt over time to improve precision,
Externí odkaz:
http://arxiv.org/abs/2401.05240
Autor:
Ponti, Moacir Antonelli, Oliveira, Lucas de Angelis, Esteban, Mathias, Garcia, Valentina, Román, Juan Martín, Argerich, Luis
Real world datasets contain incorrectly labeled instances that hamper the performance of the model and, in particular, the ability to generalize out of distribution. Also, each example might have different contribution towards learning. This motivate
Externí odkaz:
http://arxiv.org/abs/2210.11327
Autor:
Palma, Leandro, Argerich, Luis
In this work we present a modification in the conventional flow of information through a LSTM network, which we consider well suited for RNNs in general. The modification leads to a iterative scheme where the computations performed by the LSTM cell a
Externí odkaz:
http://arxiv.org/abs/1807.09830
In recent studies [1][13][12] Recurrent Neural Networks were used for generative processes and their surprising performance can be explained by their ability to create good predictions. In addition, data compression is also based on predictions. What
Externí odkaz:
http://arxiv.org/abs/1705.00697
Autor:
Argerich, Luis, Golmar, Natalia
In this paper we propose the creation of generic LSH families for the angular distance based on Johnson-Lindenstrauss projections. We show that feature hashing is a valid J-L projection and propose two new LSH families based on feature hashing. These
Externí odkaz:
http://arxiv.org/abs/1704.04684
Publikováno v:
45 JAIIO - ASAI 2016 - ISSN: 2451-7585 - Pages 33-40
In this paper we propose the application of feature hashing to create word embeddings for natural language processing. Feature hashing has been used successfully to create document vectors in related tasks like document classification. In this work w
Externí odkaz:
http://arxiv.org/abs/1608.08940
Publikováno v:
44 JAIIO - ASAI 2015 - ISSN: 2451-7585, pages 65-72
This article presents new alternatives to the similarity function for the TextRank algorithm for automatic summarization of texts. We describe the generalities of the algorithm and the different functions we propose. Some of these variants achieve a
Externí odkaz:
http://arxiv.org/abs/1602.03606
Autor:
Argerich, Luis
This report presents a very simple algorithm for overlaping community-detection in large graphs under constraints such as the minimum and maximum number of members allowed. The algorithm is based on the simulation of random walks and measures the ent
Externí odkaz:
http://arxiv.org/abs/1505.02406
Publikováno v:
Inteligencia Artificial: Revista Iberoamericana de Inteligencia Artificial; Jun2018, Vol. 21 Issue 61, p30-46, 17p