Search Results for author:
Found 19 papers, 7 papers with code
Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili
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
Very Low Resource Sentence Alignment: Luhya and Swahili
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%.
Learning to Detect Interesting Anomalies
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.
COMET-QE and Active Learning for Low-Resource Machine Translation
Active learning aims to deliver maximum benefit when resources are scarce.
Low-Resource Neural Machine Translation for Southern African Languages
Motivated by this challenge we compare zero-shot learning, transfer learning and multilingual learning on three Bantu languages (Shona, isiXhosa and isiZulu) and English.
Astronomaly: Personalised Active Anomaly Detection in Astronomical Data
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
Deep Evolution for Facial Emotion Recognition
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.
Climate & BCG: Effects on COVID-19 Death Growth Rates
Multiple studies have suggested the spread of COVID-19 is affected by factors such as climate, BCG vaccinations, pollution and blood type.
Deep Learning improves identification of Radio Frequency Interference
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
A Flexible Framework for Anomaly Detection via Dimensionality Reduction
Anomaly detection is challenging, especially for large datasets in high dimensions.
Bayesian Anomaly Detection and Classification
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.
DeepSource: Point Source Detection using Deep Learning
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.
Automated Classification of Text Sentiment
The ability to identify sentiment in text, referred to as sentiment analysis, is one which is natural to adult humans.
Painting galaxies into dark matter halos using machine learning
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
EDEN: Evolutionary Deep Networks for Efficient Machine Learning
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.
Text Compression for Sentiment Analysis via Evolutionary Algorithms
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.
Automated Problem Identification: Regression vs Classification via Evolutionary Deep Networks
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.
Application of Bayesian graphs to SN Ia data analysis and compression
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
A Measurement of the Quadrupole Power Spectrum in the Clustering of the 2dF QSO Survey
We report a measurement of the quadrupole power spectrum in the two degree field (2dF) QSO redshift (2QZ) survey.
astro-ph
