Toc, toc, toc. En algún lugar de Berlín a comienzos del siglo XX, tras esos pequeños tres golpes, se podía observar inconfundibles caras de asombro entre los periodistas y curiosos. En cambio, Wilhelm Von Osten reflejaba en su rostro algo más: felicidad, realización y por qué no, el disfrute de
Tag: LIME
Explícate! Entendiendo los modelos de Machine Learning (Parte IV: LIME, una nueva esperanza)
Explaining complex models in SAS® Viya® with programmatic interpretability
In the preceding two posts, we looked at issues around interpretability of modern black-box machine-learning models and introduced SAS® Model Studio within SAS® Visual Data Mining and Machine Learning. Now we turn our attention to programmatic interpretability.
Improving model interpretability with LIME
We have updated our software for improved interpretability since this post was written. For the latest on this topic, read our new series on model-agnostic interpretability. While some machine learning models – like decision trees – are transparent, the majority of models used today – like deep neural networks, random forests, gradient boosting