Great book! I especially liked the chapter on interpretability.
Is there anywhere in the book where you distinguish between interpretability and explainability?
In my opinion a subsection on Gradient-based explanation methods would be nice, as grad-cam is popular (at least when I read papers on explainability) and to ao distinguish saliency maps from grad-cam.
Are you also planning on writing a chapter on PINNs?
It's in a footnote of the interpretability chapter:
> What do interpretability and explainability exactly mean? Even researchers in this field can’t decide on a definition (Flora et al. 2022). From an application-oriented perspective, it’s most useful to treat these terms interchangeably. Under these keywords, you find approaches that allow you to extract information from the model about how it makes predictions.
And regarding PINNs: You are the second person to suggest this. We will definitely look into this and it might be a great addition to the domain knowledge chapter. If you have a good resource on this, would be great if you could share!
Great book! I especially liked the chapter on interpretability.
Is there anywhere in the book where you distinguish between interpretability and explainability?
In my opinion a subsection on Gradient-based explanation methods would be nice, as grad-cam is popular (at least when I read papers on explainability) and to ao distinguish saliency maps from grad-cam.
Are you also planning on writing a chapter on PINNs?
It's in a footnote of the interpretability chapter:
> What do interpretability and explainability exactly mean? Even researchers in this field can’t decide on a definition (Flora et al. 2022). From an application-oriented perspective, it’s most useful to treat these terms interchangeably. Under these keywords, you find approaches that allow you to extract information from the model about how it makes predictions.
And regarding PINNs: You are the second person to suggest this. We will definitely look into this and it might be a great addition to the domain knowledge chapter. If you have a good resource on this, would be great if you could share!
Thanks! I overlooked the footnote.
This is a good starting point on PINNs and a bit broader:
https://www.linkedin.com/posts/holger-marschall_221107377pdf-activity-7157659019371827200-8sQH
This linkedin post has several papers and software: https://www.linkedin.com/posts/steevebrechmann_datadriven-machinelearning-artificialintelligence-activity-7129542742476492802-Cxny/