Search Results for author: Oluwafemi Azeez

Found 6 papers, 0 papers with code

Proceedings of the NeurIPS 2021 Workshop on Machine Learning for the Developing World: Global Challenges

no code implementations10 Jan 2023 Paula Rodriguez Diaz, Tejumade Afonja, Konstantin Klemmer, Aya Salama, Niveditha Kalavakonda, Oluwafemi Azeez, Simone Fobi

These are the proceedings of the 5th workshop on Machine Learning for the Developing World (ML4D), held as part of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS) on December 14th, 2021.

Learning Nigerian accent embeddings from speech: preliminary results based on SautiDB-Naija corpus

no code implementations12 Dec 2021 Tejumade Afonja, Oladimeji Mudele, Iroro Orife, Kenechi Dukor, Lawrence Francis, Duru Goodness, Oluwafemi Azeez, Ademola Malomo, Clinton Mbataku

We describe how the corpus was created and curated as well as preliminary experiments with accent classification and learning Nigerian accent embeddings.

Classification

Proceedings of the NeurIPS 2020 Workshop on Machine Learning for the Developing World: Improving Resilience

no code implementations12 Jan 2021 Tejumade Afonja, Konstantin Klemmer, Aya Salama, Paula Rodriguez Diaz, Niveditha Kalavakonda, Oluwafemi Azeez

These are the proceedings of the 4th workshop on Machine Learning for the Developing World (ML4D), held as part of the Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS) on Saturday, December 12th 2020.

BIG-bench Machine Learning

Differentiable Histogram with Hard-Binning

no code implementations20 Nov 2020 Ibrahim Yusuf, George Igwegbe, Oluwafemi Azeez

The simplicity and expressiveness of a histogram render it a useful feature in different contexts including deep learning.

Agent Probing Interaction Policies

no code implementations21 Nov 2019 Siddharth Ghiya, Oluwafemi Azeez, Brendan Miller

Reinforcement learning in a multi agent system is difficult because these systems are inherently non-stationary in nature.

reinforcement-learning Reinforcement Learning (RL)

Unsupervised Domain Adaptation by Optical Flow Augmentation in Semantic Segmentation

no code implementations20 Nov 2019 Oluwafemi Azeez

It is expensive to generate real-life image labels and there is a domain gap between real-life and simulated images, hence a model trained on the latter cannot adapt to the former.

Optical Flow Estimation Segmentation +2

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