An example of how Neural Networks are excellent function approximators.Why neural networks are so good and why we should care.May 20May 20
Turning the ‘Black Boxness’ of Neural Networks into a Privacy feature.How we can harness the lack of Interpretability of neural nets for privacy preserving AI.Feb 7Feb 7
It’s possible to reconstruct a dataset’s datapoint from its mean.A simple example of how to reverse engineer the mean to get the explicit data used to compute it, and how to mitigate it.Jan 22Jan 22
How can we gauge how good a machine unlearning algorithm is?Using differential privacy to construct a gauge meter for machine unlearning.Dec 24, 2023Dec 24, 2023
Training a Transformer (BERT) Model on Swahili Text Classification Part II.Continuation.Oct 22, 2023Oct 22, 2023
Training a Transformer (BERT) Model on Swahili Text Classification Part I.Introduction.Oct 9, 2023Oct 9, 2023
