7 citations · 24 across the 11 of their papers we have counts for
11 papers
AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR
Tobi Olatunji, Tejumade Afonja, Aditya Yadavalli +8
Africa has a very low doctor-to-patient ratio. At very busy clinics, doctors could see 30+ patients per day -- a heavy patient burden compared with developed countries -- but produ…
AfriNames: Most ASR models "butcher" African Names
Tobi Olatunji, Tejumade Afonja, Bonaventure F. P. Dossou +4
Useful conversational agents must accurately capture named entities to minimize error for downstream tasks, for example, asking a voice assistant to play a track from a certain art…
Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languages
Idris Abdulmumin, Michael Beukman, Jesujoba O. Alabi +8
We participated in the WMT 2022 Large-Scale Machine Translation Evaluation for the African Languages Shared Task. This work describes our approach, which is based on filtering the…
Why is Pruning at Initialization Immune to Reinitializing and Shuffling?
Sahib Singh, Rosanne Liu
Recent studies assessing the efficacy of pruning neural networks methods uncovered a surprising finding: when conducting ablation studies on existing pruning-at-initialization meth…
WeightScale: Interpreting Weight Change in Neural Networks
Ayush Manish Agrawal, Atharva Tendle, Harshvardhan Sikka +1
Interpreting the learning dynamics of neural networks can provide useful insights into how networks learn and the development of better training and design approaches. We present a…
Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples
Nelson Manohar-Alers, Ryan Feng, Sahib Singh +2
We present DeClaW, a system for detecting, classifying, and warning of adversarial inputs presented to a classification neural network. In contrast to current state-of-the-art meth…
Benchmarking Differential Privacy and Federated Learning for BERT Models
Priyam Basu, Tiasa Singha Roy, Rakshit Naidu +3
Natural Language Processing (NLP) techniques can be applied to help with the diagnosis of medical conditions such as depression, using a collection of a person's utterances. Depres…
DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?
Archit Uniyal, Rakshit Naidu, Sasikanth Kotti +4
Recent advances in differentially private deep learning have demonstrated that application of differential privacy, specifically the DP-SGD algorithm, has a disparate impact on dif…
Investigating Learning in Deep Neural Networks using Layer-Wise Weight Change
Ayush Manish Agrawal, Atharva Tendle, Harshvardhan Sikka +2
Understanding the per-layer learning dynamics of deep neural networks is of significant interest as it may provide insights into how neural networks learn and the potential for bet…
Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy
Tom Farrand, Fatemehsadat Mireshghallah, Sahib Singh +1
Deployment of deep learning in different fields and industries is growing day by day due to its performance, which relies on the availability of data and compute. Data is often cro…
Benchmarking Differentially Private Residual Networks for Medical Imagery
Sahib Singh, Harshvardhan Sikka, Sasikanth Kotti +1
In this paper we measure the effectiveness of -Differential Privacy (DP) when applied to medical imaging. We compare two robust differential privacy mechanisms: Local-DP and DP-…