A taxonomy of surprise definitions
- URL: http://arxiv.org/abs/2209.01034v1
- Date: Fri, 2 Sep 2022 13:07:15 GMT
- Title: A taxonomy of surprise definitions
- Authors: Alireza Modirshanechi, Johanni Brea, Wulfram Gerstner
- Abstract summary: We identify 18 mathematical definitions of surprise in a unifying framework.
We classify them into four conceptual categories based on the quantity they measure.
The taxonomy poses the foundation for principled studies of the functional roles and physiological signatures of surprise in the brain.
- Score: 4.849550522970841
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Surprising events trigger measurable brain activity and influence human
behavior by affecting learning, memory, and decision-making. Currently there
is, however, no consensus on the definition of surprise. Here we identify 18
mathematical definitions of surprise in a unifying framework. We first propose
a technical classification of these definitions into three groups based on
their dependence on an agent's belief, show how they relate to each other, and
prove under what conditions they are indistinguishable. Going beyond this
technical analysis, we propose a taxonomy of surprise definitions and classify
them into four conceptual categories based on the quantity they measure: (i)
'prediction surprise' measures a mismatch between a prediction and an
observation; (ii) 'change-point detection surprise' measures the probability of
a change in the environment; (iii) 'confidence-corrected surprise' explicitly
accounts for the effect of confidence; and (iv) 'information gain surprise'
measures the belief-update upon a new observation. The taxonomy poses the
foundation for principled studies of the functional roles and physiological
signatures of surprise in the brain.
Related papers
- Reasoning about unpredicted change and explicit time [10.220888127527152]
Reasoning about unpredicted change consists in explaining observations by events.
We propose here an approach for explaining time-stamped observations by surprises, which are simple events consisting in the change of the truth value of a fluent.
arXiv Detail & Related papers (2024-07-09T07:49:57Z) - VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability [15.864519662894034]
We visualize and quantify the predictive uncertainty of gradient-based visual explanations for neural networks.
Visual post hoc explainability techniques highlight features within an image to justify a network's prediction.
We show that every image, network, prediction, and explanatory technique has a unique uncertainty.
arXiv Detail & Related papers (2024-06-01T23:32:29Z) - A Dual-Perspective Approach to Evaluating Feature Attribution Methods [43.16453263420591]
We propose two new perspectives within the faithfulness paradigm that reveal intuitive properties: soundness and completeness.
Soundness assesses the degree to which attributed features are truly predictive features, while completeness examines how well the resulting attribution reveals all the predictive features.
We apply these metrics to mainstream attribution methods, offering a novel lens through which to analyze and compare feature attribution methods.
arXiv Detail & Related papers (2023-08-17T12:41:04Z) - A Semantic Approach to Decidability in Epistemic Planning (Extended
Version) [72.77805489645604]
We use a novel semantic approach to achieve decidability.
Specifically, we augment the logic of knowledge S5$_n$ and with an interaction axiom called (knowledge) commutativity.
We prove that our framework admits a finitary non-fixpoint characterization of common knowledge, which is of independent interest.
arXiv Detail & Related papers (2023-07-28T11:26:26Z) - Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are
Conditional Entropy and Mutual Information Appropriate Measures? [2.1655448059430222]
quantify aleatoric and epistemic uncertainty in terms of conditional entropy and mutual information.
We identify various incoherencies that call their appropriateness into question.
Experiments across different computer vision tasks support our theoretical findings.
arXiv Detail & Related papers (2022-09-07T17:05:20Z) - What Should I Know? Using Meta-gradient Descent for Predictive Feature
Discovery in a Single Stream of Experience [63.75363908696257]
computational reinforcement learning seeks to construct an agent's perception of the world through predictions of future sensations.
An open challenge in this line of work is determining from the infinitely many predictions that the agent could possibly make which predictions might best support decision-making.
We introduce a meta-gradient descent process by which an agent learns what predictions to make, 2) the estimates for its chosen predictions, and 3) how to use those estimates to generate policies that maximize future reward.
arXiv Detail & Related papers (2022-06-13T21:31:06Z) - Measuring Fairness of Text Classifiers via Prediction Sensitivity [63.56554964580627]
ACCUMULATED PREDICTION SENSITIVITY measures fairness in machine learning models based on the model's prediction sensitivity to perturbations in input features.
We show that the metric can be theoretically linked with a specific notion of group fairness (statistical parity) and individual fairness.
arXiv Detail & Related papers (2022-03-16T15:00:33Z) - Empirical Estimates on Hand Manipulation are Recoverable: A Step Towards
Individualized and Explainable Robotic Support in Everyday Activities [80.37857025201036]
Key challenge for robotic systems is to figure out the behavior of another agent.
Processing correct inferences is especially challenging when (confounding) factors are not controlled experimentally.
We propose equipping robots with the necessary tools to conduct observational studies on people.
arXiv Detail & Related papers (2022-01-27T22:15:56Z) - Ensemble-based Uncertainty Quantification: Bayesian versus Credal
Inference [0.0]
We consider ensemble-based approaches to uncertainty quantification.
We specifically focus on Bayesian methods and approaches based on so-called credal sets.
The effectiveness of corresponding measures is evaluated and compared in an empirical study on classification with a reject option.
arXiv Detail & Related papers (2021-07-21T22:47:24Z) - Nested Counterfactual Identification from Arbitrary Surrogate
Experiments [95.48089725859298]
We study the identification of nested counterfactuals from an arbitrary combination of observations and experiments.
Specifically, we prove the counterfactual unnesting theorem (CUT), which allows one to map arbitrary nested counterfactuals to unnested ones.
arXiv Detail & Related papers (2021-07-07T12:51:04Z) - DEUP: Direct Epistemic Uncertainty Prediction [56.087230230128185]
Epistemic uncertainty is part of out-of-sample prediction error due to the lack of knowledge of the learner.
We propose a principled approach for directly estimating epistemic uncertainty by learning to predict generalization error and subtracting an estimate of aleatoric uncertainty.
arXiv Detail & Related papers (2021-02-16T23:50:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.