A practical decision framework for four foundational measures - Entropy, KL divergence/cross-entropy, Mutual Information, and Transfer Entropy is provided, organized around three prescriptive questions for each: what question does the measure answer and in which AI context; which estimator is appropriate for the data type and dimensionality; and what is the most dangerous misuse.
Abstract
Information-theoretic (IT) measures are ubiquitous in artificial intelligence: entropy drives decision-tree splits and uncertainty quantification, cross-entropy is the default classification loss, mutual information underpins representation learning and feature selection, and transfer entropy reveals directed influence in dynamical systems. Despite wide adoption, measure selection is often decoupled from estimator assumptions, failure modes, and safe inferential claims. This survey provides a practical decision framework for four foundational measures - Entropy, KL divergence/cross-entropy, Mutual Information, and Transfer Entropy - organized around three prescriptive questions for each: (i) what question does the measure answer and in which AI context; (ii) which estimator is appropriate for the data type and dimensionality; and (iii) what is the most dangerous misuse. The framework is operationalized in two complementary artifacts: a measure-selection flowchart and a master decision table. We cover both AI/ML and decision-making agent application domains per measure, with standardized Bridge notes linking IT quantities to cognitive and neuroscientific constructs. Two worked examples illustrate the framework on concrete practitioner scenarios spanning representation learning and temporal influence analysis, and a reproducible multi-agent case study across three learning architectures validates the transfer-entropy surrogate-testing guardrail against a null control.
Machine learning procedures are commonly evaluated in terms of predictive accuracy and computational efficiency. However, their achievable performance is fundamentally constrained by structural properties of the underlying data-generating process, which are formalized in terms of informational bounds. In this work we examine intrinsic limits of data-driven decision systems from an information-theoretic and interaction-based perspective. We analyze minimal achievable error in classification through Fano-type bounds and precision limits in parametric estimation via the Cram\'er-Rao inequality, emphasizing that such limits depend on the underlying model rather than on algorithmic sophistication alone. We further discuss how implicit assumptions, such as independence, ergodicity, and distributional stability, affect the validity of inferential procedures. Building on interaction-based modeling principles, we review typical frameworks such as Markov Random Fields and potential based representations for encoding dependence mechanisms. We also describe decision systems, including LLM-integrated agent architectures, as feedback-driven stochastic processes where state-dependent dynamics may induce emergent macroscopic behavior. This perspective highlights the importance of having adequate models for the data as a prerequi- site for expanding predictive capability, and situates algorithmic learning within the informational limits imposed by the models.
: Accuracy alone is insufficient for machine learning systems that support high-stakes decisions under uncertainty and distribution shift. This paper proposes a trust-centric framework that integrates ensemble-based uncertainty estimation, maximum mean discrepancy (MMD) shift detection, a dependability signal, and safety-aware decision logic to prioritize reliable actions over raw predictive confidence. The framework first estimates prediction reliability and then modulates action selection through feasibility constraints and a conservative fall-back policy when dependability is low. Evaluation on three high-stakes decision scenarios under controlled distribution-shift stress tests shows that the proposed framework reduces high-confidence errors from 18.3% to 6.8%, decreases constraint violations from 12.7% to 1.4%, and improves decision stability from 0.42 to 0.22 relative to an accuracy-only baseline, while maintaining competitive average utility. Ablation results further show that uncertainty weighting, shift detection, and fallback control each contribute to these gains. These findings support the need for reliability-aware, constraint-aware decision systems in safety-critical applications.
Yusuf Surajo, S. Basri, A. Balogun et al.· Proceedings of the 21st Inte...· 0 citations
Many signal processing systems ultimately exist to {act}. Whenever the state variable that determines the action to be taken by a decision maker, or agent, is uncertain, the way that uncertainty is represented decides how well the agent performs and how much its performance can be trusted. This lecture note develops, from first principles and within a single decision-theoretic setting, the link between the {objective} and the knowledge of an agent and the form of uncertainty representation that is sufficient to act optimally. To start, assuming a known environment distribution, we show that a risk-neutral agent needs the posterior distribution over the state, whereas a risk-averse agent can rely without loss of optimality on a {prediction set} and a worst-case decision rule. We then turn to the case in which the environment is unknown, and identify three complementary approaches to address the resulting epistemic uncertainty: calibration of a fixed predictor, credal (ambiguity) sets with distributionally robust optimization, and Bayesian inference over model parameters. The common thread is that reliable decisions require an uncertainty representation matched to the decision objective and to the knowledge profile of the agent, together with a guarantee that certifies the utility the agent will actually obtain.
Artificial Intelligence (AI) has revolutionized decision-making systems of today, allowing automated data analysis, intelligent prediction, and real-time decision-making in a variety of application areas, including healthcare, finance, transportation, manufacturing, cybersecurity, and public administration. While deep learning and other advanced machine learning techniques have been able to deliver impressive results, numerous AI models can be considered as ‘black-box’ models, meaning that they give very accurate predictions without actually offering understandable explanations for their decisions. This lack of transparency has generated a number of concerns about trust, accountability, fairness, ethical compliance, and regulatory acceptance. Explainable Artificial Intelligence (XAI) is thus becoming an indispensable research field which aims to reconcile the predictive power and human interpretability. By explaining the reasoning behind AI system output, model importance, feature impact, and confidence scores, XAI helps users gain insights into how the system is working. This is done to build trust among stakeholders and promote responsible AI governance and decision-making. This paper offers a detailed overview of the concept of Explainable AI in contemporary decision-making processes, covering its theoretical underpinnings, its development, prominent explainability methods, implementation in practice, hurdles, and prospects. A methodology is advanced to embed explainability in the AI decision-making process, starting from data preprocessing to generating explanations and human evaluation. The paper also delves into the implications of explainability on decision quality, user trust, model reliability, and regulatory compliance. The results highlight the potential of explainability to enhance human comprehension and foster responsible use of AI systems in high-stakes decision-making scenarios.
Mahabala H.N· International Journal of Mod...· 0 citations
Neural networks increasingly guide decisions in high-stakes domains such as medical diagnosis, credit approval, and energy bidding. Audit in these settings requires case-level evidence: which training cases support an action and what outcomes they carried. Case-based decision theory (CBDT) formalizes this reasoning by aggregating outcome support from remembered cases. We show that an OLS action readout fitted on a fixed neural representation admits an exact case-based decomposition. Each action score is a weighted sum of training-case returns, with coefficients determined by empirical Gram geometry. We identify a sufficient regime for CBDT similarity semantics; outside it, the coefficients should generally be treated as signed Gram-geometric influence. The decomposition yields audit signals that trace scores to training cases, measure action coherence, and identify weak support. Across synthetic CBDT, PJM, Adult Income, and Default Credit tasks, the method recovers case-level preference structure and achieves the highest mean Top-30 consistency among compared attribution baselines, while remaining competitive on support reconstruction. The audit requires only fitting an OLS top-layer probe, without retraining the representation or accessing the original optimization trajectory; probe fidelity is measured by score reconstruction.
Manli Yan, Yu-Erh Lin, Yaowen Yu et al.· 1 citation
It is shown that a key factor is the error correlation structure between human and AI predictions, and when the AI's prediction errors are negatively correlated with those of the human, the decision maker can construct robust strategies which guarantee improvements in expected utility.