Explainable Machine Learning (INFD11019)
Explainable Machine Learning (INFD11019)
Media for the School of Informatics course Explainable Machine Learning: A Practical Introduction (INFD11019).
Artificial intelligence (AI) provides many opportunities to improve private and public life. Discovering patterns and structures in large troves of data in an automated manner is a core component of data science, and currently drives applications in diverse areas such as computational biology, law and finance. However, such a highly positive impact is coupled with significant challenges: how do we understand the decisions suggested by these systems in order that we can trust them? In this course, we focus specifically on data driven methods - machine learning (ML) and pattern recognition models in particular - so as to survey and distill the results and observations from the literature. The purpose of this course is to provide and explore the principles and practice of enabling explainability in machine learning models. The course builds a narrative around a putative data scientist, and discusses how she might go about explaining her models by asking the right questions.
Here you will find the pre-recorded lectures, recordings of the interactive online sessions and tutorial sessions.
Here you will find the pre-recorded lectures, recordings of the interactive online sessions and tutorial sessions.
-
Introduction of a teaching assistant Giannis Papantonis.
Teaching Team Introductions - Giannis Papantonis
-
Introduction of a teaching assistant Ionela Mocanu.
Teaching Team Introductions - Ionela Mocanu
-
This lecture will cover theoretical aspects of PDP and ICE, explaining how both methods operate.
XAI Lecture Recording: PDP/ICE (Part 3)
-
This lecture will cover theoretical aspects of PDP and ICE, explaining how both methods operate.
XAI Lecture Recording: PDP/ICE (Part 2)
-
This lecture will cover theoretical aspects of PDP and ICE, explaining how both methods operate.
XAI Lecture Recording: PDP/ICE (Part 1)
-
This lecture will cover InTrees, which is a model-specific XAI method for tree ensembles.
XAI Lecture Recording: InTrees (Part 3)
-
This lecture will cover InTrees, which is a model-specific XAI method for tree ensembles.
XAI Lecture Recording: InTrees (Part 2)
-
This lecture will cover InTrees, which is a model-specific XAI method for tree ensembles.
XAI Lecture Recording: InTrees (Part 1)
-
This lecture will cover the Anchors approach for XAI.
XAI Lecture Recording - Anchors (Part 2)
-
This lecture will cover the Anchors approach for XAI.
XAI Lecture Recording - Anchors (Part 1)
-
This lecture will discuss the future of XAI.
XAI Lecture Recording - Future Directions (Part 3)
-
This lecture will discuss the future of XAI.
XAI Lecture Recording - Future Directions (Part 2)
-
This lecture will discuss the future of XAI.
XAI Lecture Recording - Future Directions (Part 1)
-
This lecture will cover the Deletion Diagnostics technique.
XAI Lecture Recording - Deletion Diagnostics…
-
This lecture will cover the Deletion Diagnostics technique.
XAI Lecture Recording - Deletion Diagnostics…
Search for ""
Public, Restricted
34
Media
8
Members
- Managers:
- Appears In: