Fibres of Failure: Classifying errors in predictive processes
We describe Fibres of Failure (FiFa), a method to classify failure modes of predictive processes using the Mapper algorithm from Topological Data Analysis. Our method uses Mapper to build a graph model of input data stratified by prediction error. Groupings found in high-error regions of the Mapper model then provide distinct failure modes of the predictive process. We demonstrate FiFa on misclassifications of MNIST images with added noise, and demonstrate two ways to use the failure mode classification: either to produce a correction layer that adjusts predictions by similarity to the failure modes; or to inspect members of the failure modes to illustrate and investigate what characterizes each failure mode.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationTopological Data AnalysisSimilar Papers 제목 키워드 기반
In-situ crosslinked wet spun collagen triple helices with nanoscale-regulated ciprofloxacin release capability
The design of antibacterial-releasing coatings or wrapping materials with controlled drug release capability is a promising strategy to minimise risks of infection and medical device failure in vivo. Collagen fibres have…
Multiscale Modelling of Fibres Dynamics and Cell Adhesion within Moving Boundary Cancer Invasion
Cancer cell invasion is recognised as one of the hallmarks of cancer and involves several inner-related multiscale processes that ultimately contribute to its spread into the surrounding tissue. In order to gain a deeper…
Training Models to Detect Successive Robot Errors from Human Reactions
As robots become more integrated into society, detecting robot errors is essential for effective human-robot interaction (HRI). When a robot fails repeatedly, how can it know when to change its behavior? Humans naturally…
Automatic and Efficient Customization of Neural Networks for ML Applications
ML APIs have greatly relieved application developers of the burden to design and train their own neural network models -- classifying objects in an image can now be as simple as one line of Python code to call an API. Ho…
ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures
Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-hoc correction mechanisms or operate under fixed task decompositions…