Search Results for author: John Keane

Found 7 papers, 4 papers with code

Using Interaction Data to Predict Engagement with Interactive Media

1 code implementation4 Aug 2021 Jonathan Carlton, Andy Brown, Caroline Jay, John Keane

The results demonstrate that interaction data can be used to infer users' engagement during and after an experience, and the proposed techniques are relevant to better understand audience preference and responses.

Adaptive Weighting Scheme for Automatic Time-Series Data Augmentation

no code implementations16 Feb 2021 Elizabeth Fons, Paula Dawson, Xiao-jun Zeng, John Keane, Alexandros Iosifidis

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

Audio Classification Data Augmentation +4

HAWKS: Evolving Challenging Benchmark Sets for Cluster Analysis

2 code implementations13 Feb 2021 Cameron Shand, Richard Allmendinger, Julia Handl, Andrew Webb, John Keane

Here, we argue that synthetic datasets must continue to play an important role in the evaluation of clustering algorithms, but that this necessitates constructing benchmarks that appropriately cover the diverse set of properties that impact clustering algorithm performance.

Benchmark

Augmenting transferred representations for stock classification

no code implementations28 Oct 2020 Elizabeth Fons, Paula Dawson, Xiao-jun Zeng, John Keane, Alexandros Iosifidis

In this paper we show that using transfer learning can help with this task, by pre-training a model to extract universal features on the full universe of stocks of the S$\&$P500 index and then transferring it to another model to directly learn a trading rule.

Classification Data Augmentation +3

Evaluating data augmentation for financial time series classification

1 code implementation28 Oct 2020 Elizabeth Fons, Paula Dawson, Xiao-jun Zeng, John Keane, Alexandros Iosifidis

Data augmentation methods in combination with deep neural networks have been used extensively in computer vision on classification tasks, achieving great success; however, their use in time series classification is still at an early stage.

Classification Computer Vision +4

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

no code implementations28 Feb 2019 Elizabeth Fons, Paula Dawson, Jeffrey Yau, Xiao-jun Zeng, John Keane

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 institutional investors.

feature selection

Breaking the Activation Function Bottleneck through Adaptive Parameterization

1 code implementation NeurIPS 2018 Sebastian Flennerhag, Hujun Yin, John Keane, Mark Elliot

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

Cannot find the paper you are looking for? You can Submit a new open access paper.