ICM: An Intuitive Model Independent and Accurate Certainty Measure for Machine Learning

  title={ICM: An Intuitive Model Independent and Accurate Certainty Measure for Machine Learning},
  author={J. V. D. Waa and J. Diggelen and M. Neerincx and S. Raaijmakers},
End-users of machine learning-based systems benefit from measures that quantify the trustworthiness of the underlying models. Measures like accuracy provide for a general sense of model performance, but offer no detailed information on specific model outputs. Probabilistic outputs, on the other hand, express such details, but they are not available for all types of machine learning, and can be heavily influenced by bias and lack of representative training data. Further, they are often difficult… Expand
9 Citations
The Design and Validation of an Intuitive Confidence Measure
  • 1
  • PDF
Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges
  • 33
  • Highly Influenced
  • PDF
Learning Human Intention for Taskable Agents
  • 2019
L G ] 1 0 M ay 2 01 9 Assuring the Machine Learning Lifecycle : Desiderata , Methods , and Challenges
  • Highly Influenced
Towards a Theory of Longitudinal Trust Calibration in Human–Robot Teams
  • 27


Feature Importance Measure for Non-linear Learning Algorithms
  • 22
  • PDF
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
  • 4,432
  • PDF
Nothing Else Matters: Model-Agnostic Explanations By Identifying Prediction Invariance
  • 35
  • PDF
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
  • 1,910
  • PDF
Algorithmic Transparency via Quantitative Input Influence: Theory and Experiments with Learning Systems
  • 359
  • PDF
Adam: A Method for Stochastic Optimization
  • 63,337
  • PDF
A Review and Empirical Evaluation of Feature Weighting Methods for a Class of Lazy Learning Algorithms
  • 660
  • PDF
Machine Learning in Action
  • 366
  • Highly Influential
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
  • 2,653
  • PDF
Weight Uncertainty in Neural Networks
  • 1,056
  • PDF