Classification, Slippage, Failure and Discovery
This work addresses the problem of interpreting and critiquing ML systems for researchers and practitioners, but it is incremental as it builds on existing ideas of failure and critique in technology.
The paper explores how machine learning classification systems can be used for constructive technology critique through experiments in image data creation and neural network classification, focusing on slippage and the potential for discovery when these systems fail as anticipated.
This text argues for the potential of machine learning infused classification systems as vectors for a technically-engaged and constructive technology critique. The text describes this potential with several experiments in image data creation and neural network based classification. The text considers varying aspects of slippage in classification and considers the potential for discovery - as opposed to disaster - stemming from machine learning systems when they fail to perform as anticipated.