Part II - Explainable ML Models: Local post hoc explanations
Post hoc explanations approximate the behavior of a black-box by extracting relationships between feature values and the predictions. Several local explanation methods are model-agnostic, meaning they do not have access to the internal structure of the model.
Explainable ML Models: what are explanations and why do we need them? – Part I
Interpretability is a key element of trust for AI models. An explanation is an interpretable description of a model behavior. For an explanation to be valid it needs to be faithful to the model and it needs to be understandable to the user.
Redefining the Newsletter Experience
A decline in trust in media and the need to access unbiased information, are two of the many reasons why a wave of local, reader-supported newspapers is emerging. Local news publishers build a closer tie with the readers by talking about the community, city development, and the local government they
Personalization, Privacy, and Me
TL;DR At recsyslabs we are building AI powered products that provide personalized recommendations to readers without harvesting personal data. Online content personalization is not a solved problem. People are growing concerned of their data being collected in excess and the usage of it for purposes other than the ones