Výsledky vyhledávání - "Istrate, Roxana"

Report

PAGAN: Portfolio Analysis with Generative Adversarial Networks

Autor: Mariani, Giovanni, Zhu, Yada, Li, Jianbo, Scheidegger, Florian, Istrate, Roxana, Bekas, Costas, Malossi, A. Cristiano I.

Since decades, the data science community tries to propose prediction models of financial time series. Yet, driven by the rapid development of information technology and machine intelligence, the velocity of today's information leads to high market e

Externí odkaz: http://arxiv.org/abs/1909.10578

Zobrazit plný text záznamu

Report

NeuNetS: An Automated Synthesis Engine for Neural Network Design

Application of neural networks to a vast variety of practical applications is transforming the way AI is applied in practice. Pre-trained neural network models available through APIs or capability to custom train pre-built neural network architecture

Externí odkaz: http://arxiv.org/abs/1901.06261

Zobrazit plný text záznamu

Report

Incremental Training of Deep Convolutional Neural Networks

Autor: Istrate, Roxana, Malossi, Adelmo Cristiano Innocenza, Bekas, Costas, Nikolopoulos, Dimitrios

We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network, we introd

Externí odkaz: http://arxiv.org/abs/1803.10232

Zobrazit plný text záznamu

Report

Efficient Image Dataset Classification Difficulty Estimation for Predicting Deep-Learning Accuracy

Autor: Scheidegger, Florian, Istrate, Roxana, Mariani, Giovanni, Benini, Luca, Bekas, Costas, Malossi, Cristiano

In the deep-learning community new algorithms are published at an incredible pace. Therefore, solving an image classification problem for new datasets becomes a challenging task, as it requires to re-evaluate published algorithms and their different

Externí odkaz: http://arxiv.org/abs/1803.09588

Zobrazit plný text záznamu

Report

BAGAN: Data Augmentation with Balancing GAN

Autor: Mariani, Giovanni, Scheidegger, Florian, Istrate, Roxana, Bekas, Costas, Malossi, Cristiano

Image classification datasets are often imbalanced, characteristic that negatively affects the accuracy of deep-learning classifiers. In this work we propose balancing GAN (BAGAN) as an augmentation tool to restore balance in imbalanced datasets. Thi

Externí odkaz: http://arxiv.org/abs/1803.09655

Zobrazit plný text záznamu