Deep Learning Explainability
Deep Learning Explainability groups the core ideas a learner needs at the 10 · interpretation & explainability stage. Work through the lessons in order when new to the area, or use them independently as a reference when implementing an analysis.
Learn the mechanism one decision at a time
Work through the lessons in order if the topic is new. If you already know the basics, open the specific leaf lesson that matches the operation, diagnostic or failure mode you need.
1Definition→
2Mechanism→
3Example→
4Diagnostic→
5Decision
Saliency mapsSaliency maps is a practical concept within Deep Learning Explainability. It helps turn the broader workflow stage “10 · Interpretation & Explainability” into an explicit analytical decision that can be explained, implemented and checked. The concept should be understood in terms of purpose, mechanism, assumptions, evidence and downstream consequences.
02Integrated gradientsIntegrated gradients is a practical concept within Deep Learning Explainability. It helps turn the broader workflow stage “10 · Interpretation & Explainability” into an explicit analytical decision that can be explained, implemented and checked. The concept should be understood in terms of purpose, mechanism, assumptions, evidence and downstream consequences.
03Grad-CAMGrad-CAM is a practical concept within Deep Learning Explainability. It helps turn the broader workflow stage “10 · Interpretation & Explainability” into an explicit analytical decision that can be explained, implemented and checked. The concept should be understood in terms of purpose, mechanism, assumptions, evidence and downstream consequences.
04Attention visualisationAttention visualisation is a communication and diagnostic technique that maps data or results into a visual form. A useful visual makes comparisons easy, exposes uncertainty and supports the analytical question rather than merely decorating the report.
05Embedding visualisationEmbedding visualisation is a communication and diagnostic technique that maps data or results into a visual form. A useful visual makes comparisons easy, exposes uncertainty and supports the analytical question rather than merely decorating the report.
06Explanation stabilityExplanation stability is a practical concept within Deep Learning Explainability. It helps turn the broader workflow stage “10 · Interpretation & Explainability” into an explicit analytical decision that can be explained, implemented and checked. The concept should be understood in terms of purpose, mechanism, assumptions, evidence and downstream consequences.