Interpretability, Explainability, and Machine Learning – What Data Scientists Need to Know

Description

Summary

• I use one of those credit monitoring services that regularly emails me about my credit score: “ We could look at the layers of the model and their weights, but we might have a difficult time understanding what that configuration actually meant in the “real world,” or, in other words, how the layers and their weights corresponded in recognizable ways to our variables.
• In other cases, you may have to rely on quantitative measures that demonstrate how a model was constructed, but their meaning is less obviously apparent, especially for non-technical audiences.
• Adversarial patches,” or image modifications, can be used to manipulate the classifications predicted by neural networks, and in doing so, offer insight into what features the algorithm is using to generate its predictions.