Study shows how machine learning can improve human performance in deception detection.
problem Improving human performance in critical tasks involving ethical and legal concerns.
method Investigated how machine learning models and their predictions can assist humans in deception detection tasks.
result Explanations and predicted labels from machine learning models can improve human performance in deception detection.
Framework improves human decision-making by learning representations.
problem Improving human decision-making performance conflated with machine accuracy.
method Mind Composed with Machine framework, incorporating human decision-making model into representation learning.
result Empirically demonstrated successful application to various tasks and representational forms.
Human+Machine models show no advantage in recidivism prediction.
problem Improving fairness in recidivism risk assessments.
method Constructed Human Risk Score and hybrid Human+Machine models.
result Human and COMPAS decision making differed but not in ways that improved prediction.
The emerging paradigm of Human-Machine Inference Networks (HuMaINs) combines complementary cognitive strengths of humans and machines in an intelligent manner to tackle various inference tasks and achieves higher performance than either humans or machines by themselves. While inference performance optimization techniqu…
The paper offers a checklist for comparing human and machine visual perception.
problem Comparing human and machine visual perception.
method Designing, conducting, and interpreting experiments to investigate mechanisms.
result Feedback mechanisms may not be necessary for visual reasoning tasks.
Autonomous systems can substantially enhance a human's efficiency and effectiveness in complex environments. Machines, however, are often unable to observe the preferences of the humans that they serve. Despite the fact that the human's and machine's objectives are aligned, asymmetric information, along with heterogene…
Research aims to distinguish machine learning from human learning by studying tasks under human-created rules.
problem Understanding the difference between machine learning and human learning.
method Developing a novel approach to study learning under human-created rules.
result Found interesting groundtruth rule pairs to distinguish AI from human learning.
ICML workshop on making machine learning models more understandable.
problem Making machine learning models more understandable to humans.
method Various presentations and discussions on interpretability techniques.
result Advancements in methods to improve model interpretability.
Study finds resolution impacts human classification performance in MNIST data.
problem Understanding factors affecting human classification performance in machine learning.
method Empirical study of MNIST data at various resolutions.
result Derived a quantitative relationship between resolution and human classification performance.
The paper introduces a new framework for making machine learning explanations more understandable to humans.
problem Making machine learning explanations comprehensible and aligned with human preferences.
method Inspired by philosophy, cognitive science, and social sciences, the paper formalizes a framework using the concept of 'weight of evidence' from information theory.
result The framework produces intuitive and comprehensible explanations that align with human preferences.
Study improves understanding of what makes machine learning explanations human-interpretable.
problem Understanding what makes explanations human-interpretable in machine learning systems.
method Controlled human-subject experiments to identify regularizers for interpretability across three tasks.
result Cognitive chunks affect performance more than variable repetitions, suggesting common design principles.
Pandora hybridizes human and machine methods to explain AI system failures.
problem Understanding and explaining failures in complex AI systems.
method Hybrid human-machine methods and tools for summarizing system malfunction.
result Detailed performance views help in analysis and debugging of AI systems.
The abstract discusses how humans use visualizations in machine learning.
problem The reliance on human involvement in AI systems and analytics.
method Review of seven steps in the ML process and different visualization techniques.
result Different visualizations are used at various stages of the ML process.
XGL uses global explanations to guide human supervision in machine learning.
problem Improving model quality through human-machine interaction.
method XGL employs global explanations to guide human selection of informative examples.
result XGL avoids overselling the model's quality and performs comparably to other strategies.
New cognitive model priors improve human decision prediction.
problem Predicting human decisions with high precision remains challenging.
method Pretrained neural networks on synthetic data generated by cognitive models, fine-tuning on real human data.
result Fine-tuned neural networks achieve unprecedented state-of-the-art improvements on benchmark datasets.
Study evaluates human vs. machine review generation, finds human assessments correlate better with lexical overlaps.
problem Evaluating natural language generation models for online reviews is challenging and inconsistent.
method Compared human evaluators with various automated evaluation methods, including discriminative and word overlap metrics.
result Human evaluators do not correlate well with discriminative evaluators, but correlate better with lexical overlaps.
Have you ever looked at a machine learning classification model and thought, I could have made that? Well, that is what we test in this project, comparing XGBoost trained on human engineered features to training directly on data. The human engineered features do not outperform XGBoost trained di- rectly on the data, bu…
Conformal prediction sets improve human decision making by quantifying model uncertainty.
problem Humans signal uncertainty and offer alternatives when unsure, but machine learning models often lack this feature.
method Conducted a randomized controlled trial with human subjects given conformal prediction sets.
result Human accuracy improves when given conformal prediction sets compared to fixed-size prediction sets.
Develops methods for cooperative Bayesian inference.
problem Cooperation between learning agents.
method Sequential Bayesian inference approaches.
result Theoretical foundation for cooperative inference.
Paper examines how adversarial ML attacks and defenses impact civil liberties and human rights.
problem Impact of adversarial machine learning on civil liberties and human rights.
method Uses insights from STS, anthropology, and human rights literature.
result Adversarial defenses can be used to suppress dissent and limit investigation of ML systems.
New research shows machine-assisted decisions can still be unfair even when the algorithm is fair.
problem Ensuring fairness in decisions made with machine-assisted human input.
method Formal model and lab experiment to analyze how machine predictions affect human decisions.
result Excluding information about protected groups from machine predictions can increase disparities.
High-dimensional neural network manifolds misalign with human perception, causing adversarial examples.
problem Adversarial attacks fool neural networks, but their origin is unclear.
method Defined and analyzed a network's perceptual manifold (PM) for a class concept.
result Neural network PMs have orders of magnitude higher dimensions than natural human concepts, suggesting exponential misalignment.
Study human-machine interaction with private info using offline RL.
problem Confounding bias and distributional mismatch in offline RL for human-guided interaction.
method Developed a novel identification result and OPE method to address confounding bias, and used pessimism to tackle distributional mismatch.
result Policy pair converges to optimal one at satisfactory rate under mild assumptions.
Bayesian framework infers personalized embeddings for diverse human demonstrations.
problem Lack of personalized models for diverse human behaviors.
method Bayesian LfD framework inferring human-specific embeddings.
result Outperforms state-of-the-art techniques on synthetic and real-world data.
MCAL reduces labeling costs by 6x for auto-labeling data sets.
problem Expensive human annotation for ground-truth data sets.
method Iterative approach that trains a classifier to auto-label part of the data set, determining which samples to label using humans and which to label using the classifier at each step.
result 6x lower overall cost compared to human labeling the entire data set, always cheaper than competing strategies.
Framework ensures alignment between humans and machines in LLMs.
problem Human-machine misalignment in LLMs scoring mechanisms.
method Lightweight calibration framework for blackbox models.
result Provably guarantees alignment between humans and machines.
A model for human-machine decision-making with private info and opacity.
problem Optimizing decisions in a human-machine system with private info and opacity.
method Formulated as a two-player learning problem, proved lower and upper bounds on optimality.
result Simple coordination strategy is nearly minimax optimal, efficient learning possible under certain assumptions.
AutoML frameworks outperform human data scientists on 7 out of 12 OpenML tasks.
problem Evaluating if AutoML can outperform human data scientists.
method Comparison of four AutoML frameworks on 12 popular OpenML datasets (6 supervised classification, 6 supervised regression).
result AutoML frameworks perform better or equal to human data scientists in 7 out of 12 tasks.
Machine learning workflow development is anecdotally regarded to be an iterative process of trial-and-error with humans-in-the-loop. However, we are not aware of quantitative evidence corroborating this popular belief. A quantitative characterization of iteration can serve as a benchmark for machine learning workflow d…
Paper tackles regression under human assistance, showing NP-hardness and developing a greedy algorithm.
problem Optimizing machine learning models under human intervention.
method Introduced ridge regression under human assistance, derived NP-hardness, and developed a greedy algorithm.
result Greedy algorithm achieves good performance in medical diagnosis and content moderation applications.
This is the Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017), which was held in Sydney, Australia, August 10, 2017. Invited speakers were Tony Jebara, Pang Wei Koh, and David Sontag.
Survey on making machine learning models more understandable.
problem Making predictions from machine learning models transparent and understandable for humans.
method Conducts a survey on explainable supervised machine learning approaches.
result Classifies explainable SML approaches and discusses future directions.
Combines human and model predictions for improved accuracy.
problem Improving classification accuracy when both human and model predictions are imperfect.
method Uses confusion matrices and calibration to combine probabilistic model outputs with human class-level predictions.
result Human-model combinations consistently outperform either alone, with accuracy gains even with limited human input.
Interactive machine learning improves deep RL in Minecraft by giving action advice.
problem Training deep RL agents in high-aliasing environments like Minecraft is computationally expensive.
method Conducted experiments with two RL algorithms, Feedback Arbitration, and Newtonian Action Advice, to give action advice to human teachers.
result Action advice from human teachers can improve agent performance in high-aliasing environments.
This is the Proceedings of the 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016), which was held in New York, NY, June 23, 2016. Invited speakers were Susan Athey, Rich Caruana, Jacob Feldman, Percy Liang, and Hanna Wallach.
Study shows current metrics for audio adversarial examples are unreliable for human perception.
problem The reliability of metrics for evaluating audio adversarial examples.
method Analytical framework and human evaluation experiment.
result Current metrics for audio adversarial examples are not reliable for human perception.
Model predicts human food choices based on demographics.
problem Predicting human food choices from demographic data.
method Non-deterministic model based on NHANES dataset and behavioral studies.
result Generates synthetic data similar to original dataset.
Machine learning algorithms can inherit human biases, requiring fairness audits.
problem Machine learning algorithms can inherit or perpetuate human biases in decision making.
method Fairness constraints must be specific to the domain and include transparency for audits.
result Fairness in algorithms is complex and context-dependent.
Human irrationality can improve AI design, study shows.
problem Improving AI by learning from human decision-making biases.
method Developed a novel POMDP model to simulate human decision-making in contextual choice tasks.
result Reinforcement learners can exploit human irrationalities to make better decisions.
New models predict mobility flows as well as complex machine learning but are simpler and interpretable.
problem Incomplete understanding and modeling of human mobility flows.
method Developed simple machine-learned, closed-form models of mobility.
result These models predict mobility flows more accurately than gravity or complex machine/deep learning models.
We present an approach to interactive-predictive neural machine translation that attempts to reduce human effort from three directions: Firstly, instead of requiring humans to select, correct, or delete segments, we employ the idea of learning from human reinforcements in form of judgments on the quality of partial tra…
Paper proposes privacy-preserving learning for images, making them imperceptible to humans but recognizable by machines.
problem Conflict between developing AI systems and protecting sensitive training data.
method Encryption strategies (random shuffling and sub-patch mixing) followed by minimal adaptation to vision transformer.
result Achieves comparable accuracy to competitive methods while ensuring human-imperceptibility of encrypted images.
The step of expert taxa recognition currently slows down the response time of many bioassessments. Shifting to quicker and cheaper state-of-the-art machine learning approaches is still met with expert scepticism towards the ability and logic of machines. In our study, we investigate both the differences in accuracy and…
Solving the RNA inverse folding problem is a critical prerequisite to RNA design, an emerging field in bioengineering with a broad range of applications from reaction catalysis to cancer therapy. Although significant progress has been made in developing machine-based inverse RNA folding algorithms, current approaches s…
Geometric framework detects concept frustration between human concepts and machine representations.
problem Aligning human concepts with machine learning representations.
method Geometric framework and similarity measures for detecting concept frustration.
result Concept frustration affects machine learning model performance and reorganizes learned concept representations.
Machine learning aids in shark detection at Muizenberg Beach.
problem Improving shark spotting efficiency using automated methods.
method Defined desirable properties, selected mathematical techniques, and partially implemented model.
result Extract useful information from shark images despite geometric transformations.
Machine learning predicts plant phenotypes from soil microbiome data.
problem Predicting plant phenotypes from soil microbiome data.
method Two models (random forest and Bayesian neural network) were used to predict plant phenotypes from soil properties and microbial population density.
result Human decisions and normalization strategies significantly impact model performance.
This paper refines human labeling as a measurement process, revealing four sources of variation.
problem Systematic variation in human labeling obscures model learning.
method Introduces a statistical framework to decompose labeling outcomes.
result Empirical evidence for four components of labeling variation.