activity
20182021
most citedAdaptive Weighting Scheme for Automatic Time-Series Data Augmentation

17 citations · 19 across the 3 of their papers we have counts for

collaborators

6 papers

cs.LG202117 cited

Adaptive Weighting Scheme for Automatic Time-Series Data Augmentation

Elizabeth Fons, Paula Dawson, Xiao-jun Zeng +2

Data augmentation methods have been shown to be a fundamental technique to improve generalization in tasks such as image, text and audio classification. Recently, automated augment…

q-fin.ST2020

Augmenting transferred representations for stock classification

Elizabeth Fons, Paula Dawson, Xiao-jun Zeng +2

Stock classification is a challenging task due to high levels of noise and volatility of stocks returns. In this paper we show that using transfer learning can help with this task,…

q-fin.ST20202 cited

Evaluating data augmentation for financial time series classification

Elizabeth Fons, Paula Dawson, Xiao-jun Zeng +2

Data augmentation methods in combination with deep neural networks have been used extensively in computer vision on classification tasks, achieving great success; however, their us…

cs.CE2019

A novel dynamic asset allocation system using Feature Saliency Hidden Markov models for smart beta investing

Elizabeth Fons, Paula Dawson, Jeffrey Yau +2

The financial crisis of 2008 generated interest in more transparent, rules-based strategies for portfolio construction, with Smart beta strategies emerging as a trend among institu…

cs.DB2018

Data Context Informed Data Wrangling

Martin Koehler, Alex Bogatu, Cristina Civili +6

The process of preparing potentially large and complex data sets for further analysis or manual examination is often called data wrangling. In classical warehousing environments, t…

cs.LG2018

Breaking the Activation Function Bottleneck through Adaptive Parameterization

Sebastian Flennerhag, Hujun Yin, John Keane +1

Standard neural network architectures are non-linear only by virtue of a simple element-wise activation function, making them both brittle and excessively large. In this paper, we…