no code implementations • 1 Jun 2023 • Christiaan Jacobs, Nathanaël Carraz Rakotonirina, Everlyn Asiko Chimoto, Bruce A. Bassett, Herman Kamper
But in an in-the-wild test on Swahili radio broadcasts with actual hate speech keywords, the AWE model (using one minute of template data) is more robust, giving similar performance to an ASR system trained on 30 hours of labelled data.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 31 Oct 2022 • Everlyn Asiko Chimoto, Bruce A. Bassett
We fine-tune the embeddings on a small set of parallel Luhya sentences and show significant gains, improving the LaBSE alignment accuracy to 53. 3%.
no code implementations • 28 Oct 2022 • Alireza Vafaei Sadr, Bruce A. Bassett, Emmanuel Sekyi
This approach, AHUNT, shows excellent performance on MNIST, CIFAR10, and Galaxy-DESI data, significantly outperforming both standard anomaly detection and active learning algorithms with static feature spaces.
no code implementations • 27 Oct 2022 • Everlyn Asiko Chimoto, Bruce A. Bassett
Active learning aims to deliver maximum benefit when resources are scarce.
no code implementations • 1 Apr 2021 • Evander Nyoni, Bruce A. Bassett
Motivated by this challenge we compare zero-shot learning, transfer learning and multilingual learning on three Bantu languages (Shona, isiXhosa and isiZulu) and English.
1 code implementation • 21 Oct 2020 • Michelle Lochner, Bruce A. Bassett
Here we introduce Astronomaly: a general anomaly detection framework with a novel active learning approach designed to provide personalised recommendations.
Instrumentation and Methods for Astrophysics Astrophysics of Galaxies
no code implementations • 29 Sep 2020 • Emmanuel Dufourq, Bruce A. Bassett
Deep facial expression recognition faces two challenges that both stem from the large number of trainable parameters: long training times and a lack of interpretability.
1 code implementation • 10 Jul 2020 • Chris Finlay, Bruce A. Bassett
Multiple studies have suggested the spread of COVID-19 is affected by factors such as climate, BCG vaccinations, pollution and blood type.
1 code implementation • 18 May 2020 • Alireza Vafaei Sadr, Bruce A. Bassett, Nadeem Oozeer, Yabebal Fantaye, Chris Finlay
Our results strongly suggest that deep learning on simulations, boosted by transfer learning on real data, will likely play a key role in the future of RFI flagging of radio astronomy data.
Instrumentation and Methods for Astrophysics
1 code implementation • 9 Sep 2019 • Alireza Vafaei Sadr, Bruce A. Bassett, Martin Kunz
Anomaly detection is challenging, especially for large datasets in high dimensions.
no code implementations • 22 Feb 2019 • Ethan Roberts, Bruce A. Bassett, Michelle Lochner
Using simulated data with Gaussian noise, BADAC is shown to be superior to standard algorithms in both classification and anomaly detection performance in the presence of uncertainties, though with significantly increased computational cost.
1 code implementation • 7 Jul 2018 • A. Vafaei Sadr, Etienne. E. Vos, Bruce A. Bassett, Zafiirah Hosenie, N. Oozeer, Michelle Lochner
For uniformly-weighted images it achieves a Purity x Completeness (PC) score at SNR = 3 of 0. 73, compared to 0. 31 for the best PyBDSF model.
no code implementations • 5 Apr 2018 • Emmanuel Dufourq, Bruce A. Bassett
The ability to identify sentiment in text, referred to as sentiment analysis, is one which is natural to adult humans.
no code implementations • 8 Dec 2017 • Shankar Agarwal, Romeel Davé, Bruce A. Bassett
Our ML framework takes input halo properties including halo mass, environment, spin, and recent growth history, and outputs central galaxy and halo baryonic properties including stellar mass ($M_*$), star formation rate (SFR), metallicity ($Z$), neutral ($\rm HI$) and molecular ($\rm H_2$) hydrogen mass.
Astrophysics of Galaxies
no code implementations • 26 Sep 2017 • Emmanuel Dufourq, Bruce A. Bassett
Deep neural networks continue to show improved performance with increasing depth, an encouraging trend that implies an explosion in the possible permutations of network architectures and hyperparameters for which there is little intuitive guidance.
no code implementations • 20 Sep 2017 • Emmanuel Dufourq, Bruce A. Bassett
An analysis of PARSEC with eight commercial and non-commercial sentiment analysis algorithms on twelve English sentiment data sets reveals that accurate compression is possible with (0%, 1. 3%, 3. 3%) loss in sentiment classification accuracy for (20%, 50%, 75%) data compression with PARSEC using LingPipe, the most accurate of the sentiment algorithms.
1 code implementation • 3 Jul 2017 • Emmanuel Dufourq, Bruce A. Bassett
We propose the Automated Problem Identification (API) algorithm, which uses an evolutionary algorithm interface to TensorFlow to manipulate a deep neural network to decide if a dataset represents a classification or a regression problem.
3 code implementations • 28 Mar 2016 • Cong Ma, Pier-Stefano Corasaniti, Bruce A. Bassett
Overall, the results of our analysis emphasize the need for a fully consistent Bayesian statistical approach in the analysis of future large SN Ia data sets.
Cosmology and Nongalactic Astrophysics
no code implementations • 6 May 2005 • Kazuhiro Yamamoto, Masashi Nakamichi, Akinari Kamino, Bruce A. Bassett, Hiroaki Nishioka
We report a measurement of the quadrupole power spectrum in the two degree field (2dF) QSO redshift (2QZ) survey.
astro-ph