Employing XAI techniques to identify relavent search space for Evolutionary Algorithms
Employing XAI techniques to identify relavent search space for Evolutionary Algorithms

Abstract: 

XAI has stormed the world and is being pitched as single stop solution to uncover black box models. This talk is focused on how we are practically using XAI as a part of Application Lifecyle Management Modelling pipeline.
Not just for explainability but also as a method to reduce search space for evolutionary algorithms.
There is an inherent randomness associated with creating a proxy linear model when dealing with packages like LIME. Or alternative packages like SHAP. We go into how we deal with the uncertainty associated with this and repurpose them to reduce the exploration space for constrained optimization problems being solved by Evolutionary Methods.
We talk about the incremental speed we have achieved along with a deeper analysis of why we see better convergence rate when combining repurposed XAI techniques with Constrained Optimization using brute force methods.
We follow this up with how this methodology is applied to the business problem to achieve better results.

Bio: 

Coming Soon!

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Youtube
Consent to display content from - Youtube
Vimeo
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google