The paper discusses safety assessment for AI systems, focusing on machine learning models.
problem Safety assessment of AI systems, especially machine learning models, in safety-related applications.
method Analyzed AI models as statistical models and proposed a new budget allocation for AI safety.
result Safety assessment of AI systems requires a new approach focusing on the model used, not just the system.
Survey of algorithms for testing AI-driven CPS safety.
problem Testing AI-driven CPS for safety in complex environments.
method Survey of applied algorithms for safety validation.
result Survey of existing tools and techniques for safety validation.
Study on AI-driven modeling for high burnup accident-tolerant fuels in SMRs.
problem Design and optimization of high burnup accident-tolerant fuels for SMRs.
method Artificial intelligence and multi-scale modeling (neutronics, thermal hydraulics, fuel performance).
result Demonstrated the effectiveness of AI in modeling and optimizing SMR fuels.
Study evaluates saliency maps on artificial data with different backgrounds.
problem Objective evaluation of saliency methods on artificial data with varying backgrounds.
method Developed a framework to generate artificial data with synthetic lesions and a known ground truth map, evaluated two data sets with different backgrounds (Perlin noise and 2D brain MRI slices).
result Heatmaps vary strongly between saliency methods and backgrounds.
AI learns market manipulation through simulation, suggesting regulation.
problem Regulating AI to prevent market manipulation.
method Used a genetic algorithm in an artificial market simulation.
result AI discovered market manipulation as an optimal strategy.
Paper tackles anomaly detection in driving data, improving AI system performance.
problem Detecting rare anomalous driving situations in safety-critical AI systems.
method Semi-supervised multi-task learning using maneuver labels for imbalanced data.
result Improved anomaly detection performance on real-world driving data.
Artificial intelligence has impacted many aspects of human life. This paper studies the impact of artificial intelligence on economic theory. In particular we study the impact of artificial intelligence on the theory of bounded rationality, efficient market hypothesis and prospect theory.
AI triage and diagnostic system performs similarly to human doctors, with safer triage advice.
problem Improving patient care through more reliable symptom checkers.
method Prospective validation study comparing AI system to human doctors.
result AI system's accuracy in identifying conditions comparable to human doctors, with safer triage advice.
Study improves self-driving safety in dynamic environments.
problem Safe self-driving in non-stationary urban settings.
method Neurosymbolic Meta-Reinforcement Lookahead Learning (NUMERLA).
result Self-driving agents can adapt safely in real-time.
Paper verifies safety of tree ensembles in safety-critical systems.
problem Ensuring safety of machine learning in safety-critical systems.
method Extract equivalence classes and formally verify input-output mappings of tree ensembles.
result Method is practical for tree ensembles trained on low-dimensional data.
Survey on AI math foundations, focusing on neural networks.
problem Lack of rigorous mathematical foundation for AI.
method Survey and discussion of theoretical directions in AI.
result Discussion of open problems in AI math.
The paper introduces sanity tests to detect spurious correlations in AI-guided radiology systems.
problem Detecting when AI systems perform well on development data for the wrong reasons.
method Design and implementation of sanity tests to identify spurious correlations.
result Sanity tests can identify spurious correlations in AI-guided radiology systems.
The paper investigates AI robustness through experiments and statistical analysis.
problem Inaccurate AI predictions can lead to safety and adoption issues.
method Design of experiments framework to study AI classification robustness.
result AI algorithms' robustness is influenced by various factors.
Safe Bayesian optimization reduces HVAC costs by 32%.
problem Optimizing room temperature PID control for energy savings and comfort.
method Safe Contextual Bayesian Optimization.
result 32% reduction in room temperature PID control costs.
AI enhances bank credit risk management through deep learning and data analysis.
problem Inaccurate credit decisions and potential risks in bank credit risk management.
method Innovative application of AI technology, including deep learning and big data analysis.
result AI provides more accurate and comprehensive credit decision support, reducing risks and losses.
The paper shows how uncertainty quantification improves counterfactual explainability in AI.
problem Lack of foundational concepts in transparency research.
method Integrates uncertainty quantification into counterfactual explainability.
result Demonstrates competitive performance of an uncertainty-based explainer.
The theory of rational choice assumes that when people make decisions they do so in order to maximize their utility. In order to achieve this goal they ought to use all the information available and consider all the choices available to choose an optimal choice. This paper investigates what happens when decisions are m…
The paper proposes a test for trading intelligence similar to the Turing Test.
problem Determining if trading programs exhibit intelligent behavior.
method Develops a test based on the Turing Test for financial trading programs.
result Introduces a method to assess trading intelligence in financial markets.
Mathematical framework using Riemannian geometry for intelligence and consciousness.
problem Lack of a unified mathematical framework for intelligence and consciousness.
method Conceptualizes intelligence as tokens in a high-dimensional space, using Riemannian geometry to describe structure and dynamics.
result Integrates geometric concepts to offer a unified framework for intelligence and consciousness.
AI improves credit rating predictions over traditional methods.
problem Improving credit rating predictions for global corporate entities.
method Applying deep learning techniques, specifically neural networks with categorical embeddings, to a large dataset of corporate obligations.
result Deep learning models achieve adequate accuracy in predicting different credit rating classes.
Financial services need explainable AI for fair lending.
problem Challenges in credit decisioning due to compliance and ethical considerations.
method Use of explainable AI models to address fairness and ethics in lending.
result Explainable AI models improve fairness and ethics in lending decisions.
AI enhances cancer diagnostics using spectroscopy.
problem Early and accurate cancer diagnosis.
method Combining AI with spectroscopy-based techniques.
result AI improves cancer diagnostics speed and safety.
System predicts ice formation to improve road safety.
problem Improving road safety through accurate ice formation prediction.
method Combining physical models and machine learning for data correction.
result Machine learning effectively corrects incorrect data in forecasts.
This paper surveys DRL for autonomous vehicle motion planning.
problem Designing intelligent motion planning for autonomous vehicles.
method Deep Reinforcement Learning (DRL) for hierarchical motion planning.
result Survey of state-of-the-art DRL solutions for autonomous vehicle motion planning.
Success in the quest for artificial intelligence has the potential to bring unprecedented benefits to humanity, and it is therefore worthwhile to investigate how to maximize these benefits while avoiding potential pitfalls. This article gives numerous examples (which should by no means be construed as an exhaustive lis…
Deep-PrAE improves rare-event simulation for black-box systems.
problem Evaluating rare safety-critical events in learning-based systems.
method Combines deep neural networks with IS to create statistically guaranteed estimations.
result Deep-PrAE provides accurate bounds on safety-critical event probabilities.
New framework uses OR to ensure AI systems make safe decisions.
problem Ensuring generative AI systems make safe decisions as they gain autonomy.
method Developed a conceptual framework combining flow-based models and adversarial robustness.
result Increased autonomy requires new OR approaches for feasibility, robustness, and stress testing.
In recent years, China, the United States and other countries, Google and other high-tech companies have increased investment in artificial intelligence. Deep learning is one of the current artificial intelligence research's key areas. This paper analyzes and summarizes the latest progress and future research direction…
This brief note highlights some basic concepts required toward understanding the evolution of machine learning and deep learning models. The note starts with an overview of artificial intelligence and its relationship to biological neuron that ultimately led to the evolution of todays intelligent models.
AI solutions matched prosthetic control goals in a challenge.
problem Matching time-varying velocity vectors in musculoskeletal models.
method Deep reinforcement learning approaches with various modifications.
result Many solutions used similar techniques but implemented unique modifications.
Paper aims to use AI for detecting financial crimes, focusing on money laundering.
problem Financial institutions need better technologies to detect and predict financial crimes.
method Study recent works, develop a novel model for money laundering detection.
result Demonstrates a model for detecting money laundering cases with minimal human intervention.
Machine learning simplifies finance, but faces challenges.
problem Adopting machine learning in finance.
method Analyzing challenges in financial services adoption.
result Challenges in finance adoption of ML.
Unified pipeline detects multi-turn deception using geometric signals.
problem Detecting multi-turn deceptive interactions in LLMs.
method Geometric signaturization via genetic prompt optimization.
result Compact geometric model achieves high recall and F1 scores.
AIBC uses AI and blockchain for efficient resource sharing.
problem Efficient resource sharing in large-scale decentralized systems.
method Two-consensus scheme with DABFT and DPoEV.
result Predictive deep learning for optimal BFT algorithm selection.
Researchers organize and analyze a large public safety imagery dataset.
problem Efficiently organizing and analyzing a vast public safety imagery dataset.
method Hierarchical organization approach using Lincoln Laboratory Supercomputing Cluster for compute and storage.
result Successfully organized and evaluated the dataset with large-scale imagery inference across terabytes of data.
Symmetry principles help in creating better AI representations.
problem Creating efficient and generalizable AI representations.
method Using symmetry transformations to guide representation learning.
result Symmetry principles improve data efficiency and generalizability in AI.
AI improves healthcare diagnostics and predictions.
problem Data heterogeneity and model limitations in AI for health.
method Review of AI applications in health informatics.
result AI enhances disease diagnosis and prediction.
Paper tackles AI risks by customizing metrics and models.
problem AI risks are multidimensional and immaturely managed.
method Decomposes AI risks into data protection, fairness, etc., and develops metrics and models.
result Customized metrics and models reduce AI risk uncertainty.
Machine learning benefits from causal inference concepts.
problem Machine learning's hard problems are related to causality.
method Introduces key concepts linking machine learning and causal inference.
result Machine learning and AI's challenges are intertwined with causality.
Computational Intelligence (CI) is a sub-branch of Artificial Intelligence paradigm focusing on the study of adaptive mechanisms to enable or facilitate intelligent behavior in complex and changing environments. There are several paradigms of CI [like artificial neural networks, evolutionary computations, swarm intelli…
AI enhances quantitative investment for better returns and risk control.
problem Achieving stable returns through AI in quantitative investment.
method Application of AI technology in quantitative investment strategies.
result AI improves investment performance and risk management.
People who design, use, and are affected by autonomous artificially intelligent agents want to be able to \emph{trust} such agents -- that is, to know that these agents will perform correctly, to understand the reasoning behind their actions, and to know how to use them appropriately. Many techniques have been devised …
Few-shot learning improves bearing fault diagnosis with limited data.
problem Challenges in collecting sufficient fault data for robust classifier training.
method Model-Agnostic Meta-Learning (MAML) for few-shot learning.
result Framework achieves up to 25% higher accuracy than Siamese network.
Research tackles distribution shift issues in ML to improve AI reliability.
problem Distribution shift limits ML reliability and trustworthiness.
method Study three distribution shifts (perturbation, domain, modality) and investigate robustness, explainability, adaptability.
result Proposes effective solutions and fundamental insights for enhancing ML robustness, adaptability, and safety.
XAI improves transparency of machine learning algorithms.
problem Complex machine learning algorithms lack understandable explanations.
method Definition and classification of explainability, review of existing methods.
result Current explanatory methods for deep neural networks are insufficient.
The problem of replicating the flexibility of human common-sense reasoning has captured the imagination of computer scientists since the early days of Alan Turing's foundational work on computation and the philosophy of artificial intelligence. In the intervening years, the idea of cognition as computation has emerged …
New algorithms improve sampling from Bayesian deep learning models.
problem Sampling from the posterior of deep neural networks is inefficient.
method Adaptive SGMCMC algorithms with biased drift.
result Proposed algorithms significantly outperform existing methods.
Enhances crowd safety through AI and data-driven models.
problem Improving crowd safety during events.
method Innovative data collection, AI, and machine learning.
result Accurate multi-day forecasts for event planning.