Relevance Forcing: More Interpretable Neural Networks through Prior Knowledge

Add to your list(s) Download to your calendar using vCal

• Christian Etmann (University of Bremen)
• Wednesday 09 May 2018, 15:30-16:30
• MR3 Centre for Mathematical Sciences.

If you have a question about this talk, please contact Rachel Furner.

Neural networks are able to reach high accuracies across many different classification tasks. However, these ‘black-box models’ suffer from one drawback: it is generally difficult to assess how the network reached its classification decision. Nevertheless, through different relevance measures, it is possible to determine which parts of the given input contribute to the resulting output. By imposing certain penalties on this relevance, through which we can encode prior information about the problem domain, we can train models which take this information into account. If we view these relevance measures as discretized dynamical systems, we may get some insight on the reliability of their explanation.

This talk is part of the CCIMI Seminars series.

This talk is included in these lists:

• All CMS events
• All Talks (aka the CURE list)
• CCIMI
• CCIMI Seminars
• CMS Events
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• DPMMS Lists
• DPMMS info aggregator
• DPMMS lists
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• MR3 Centre for Mathematical Sciences
• School of Physical Sciences
• Statistical Laboratory info aggregator
• Trust & Technology Initiative - interesting events
• bld31
• custom
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.