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 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.
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.
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.
ALPODS AI diagnoses high-dimensional biomedical data with human-understandable explanations.
problem AI decisions in high-dimensional biomedical data are not explainable to humans.
method ALPODS method classifies data based on clusters and generates fuzzy reasoning rules.
result ALPODS provides understandable explanations for AI diagnoses.
AI assistants often give convincing but incorrect responses to match user beliefs.
problem Sycophancy in AI assistants that use human feedback.
method Examined five AI assistants across four tasks, analyzed human preference data, and compared model outputs against preference models.
result Sycophancy is a general behavior of AI assistants, driven in part by human preference judgments.
Two attention models improve human activity recognition by focusing on important signals and sensor modalities.
problem Noise and unimportant signal components in recurrent networks for human activity recognition.
method Temporal and sensor attention mechanisms with continuity constraints.
result State-of-the-art results on three datasets, showing improved understandability and mean F1 score.
Extracts decision trees from CNNs to explain concept importance.
problem Understanding how CNNs make decisions about human-understandable concepts.
method Inferring labeled concept data from CNN hidden layer activations and creating a shallow decision tree.
result Extracted decision trees accurately represent CNN classifications.
Quriosity analyzes curiosity-driven questions from diverse sources.
problem Understanding and analyzing human curiosity-driven questions.
method Collection of 13.5K questions from various sources, development of an iterative prompt improvement framework.
result 42% of questions are causal, revealing unique linguistic properties.
IDT learns human preferences from uncertain decisions, even when humans are suboptimal.
problem Learning human preferences from uncertain and suboptimal decisions.
method Inverse decision theory (IDT) framework, statistical analysis of IDT, characterizing sample complexity.
result Learning preferences is easier when decisions are more uncertain, even if humans are suboptimal.
Generative deep learning creates counterfactual states to explain Atari agent decisions.
problem Difficulty in explaining deep reinforcement learning agent decisions to humans.
method Generative deep learning to create counterfactual states.
result Counterfactual states help non-expert participants understand Atari agent decision-making.
Algorithms for equilibrium computation generally make no attempt to ensure that the computed strategies are understandable by humans. For instance the strategies for the strongest poker agents are represented as massive binary files. In many situations, we would like to compute strategies that can actually be implement…
Study of sentence representations in AI shows parallels to human learning.
problem Understanding how AI systems learn and generalize from training data.
method Diagnostic tests, performance analysis, training distribution effects, representation changes with augmentations.
result AI systems can learn abstract rules and generalize under certain conditions, similar to human zero-shot reasoning.
We conduct large-scale studies on `human attention' in Visual Question Answering (VQA) to understand where humans choose to look to answer questions about images. We design and test multiple game-inspired novel attention-annotation interfaces that require the subject to sharpen regions of a blurred image to answer a qu…
Unified model of urban consumer behavior and mobility patterns.
problem Understanding the lifestyles and infrastructure of urban regions.
method Collective matrix factorization for dual view modeling of consumer behavior and mobility.
result Unified model reveals deeper insights into consumer behavior and mobility patterns.
Interpole learns transparent decision-making policies from data.
problem Understanding human decision-making in opaque environments.
method Interpole combines belief-update and belief-action mapping estimation.
result Interpole provides interpretable models of decision-making behavior.
Explainable AI improves human decision accuracy but does not enhance it significantly.
problem Improving human decision-making through explainable AI.
method Comparing human decision accuracy with and without AI predictions, including or excluding explanations.
result Providing AI predictions improves human decision accuracy, but explanations do not significantly enhance it.
Personalized explanations improve understanding of machine learning models.
problem Improving human understanding of machine learning models and decisions.
method Deriving a conceptualization of personalized explanation, categorizing explainee data, identifying key properties, and introducing new measures.
result Identification of three key properties amendable to personalization: complexity, decision information, and presentation.
LCBM model improves image classification without human supervision.
problem Improving interpretability and generalization of unsupervised concept-based models.
method LCBM models concepts as random variables in a Bernoulli latent space, reducing the number of concepts without sacrificing performance.
result LCBM outperforms existing models in generalization and interpretability.
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 purpose of this article is to propose a new "theory," the Strategic Analysis of Financial Markets (SAFM) theory, that explains the operation of financial markets using the analytical perspective of an enlightened gambler. The gambler understands that all opportunities for superior performance arise from suboptimal …
NNs accurately predict energy eigenvalues and other physical phenomena in 1D quantum mechanics.
problem Understanding how neural networks interpret physics.
method Training NNs to predict energy eigenvalues from potentials and testing their ability to generalize.
result NNs can predict physical phenomena not learned during training, indicating a new way of understanding physics.
Generative classifiers show surprising human-like performance.
problem Comparing generative and discriminative models for object recognition.
method Built on recent advances in generative modeling to create classifiers and compared them to discriminative models.
result Generative classifiers outperform discriminative models in several key areas, including shape bias and out-of-distribution accuracy.
Synthesizes AI and human creativity for more compelling art.
problem Making AI-generated art more human-like.
method Combining Deep Learning and Cognitive Psychology theories.
result Demonstrates how AI can incorporate human creativity theories.
Parenting algorithm improves AI safety by learning from human input.
problem Safety concerns in reinforcement learning, especially reward hacking and unsafe exploration.
method Inspired by parenting, a precise framework for learning from human input.
result Parenting algorithm solves safety problems in AI Safety gridworlds.
Improves AI system's understanding of human inputs by creating better examples.
problem AI systems misinterpret human inputs, leading to inefficiencies.
method Developed a conditional convolutional autoencoder (CCAE) to generate better examples.
result Generated examples lead to lower error rates and require less effort to create.
Two KG-based methods explain transfer learning in CNN and ZSL.
problem Uninterpretable transfer learning for non-ML experts.
method Knowledge Graph-based explanation for transferability and model justification.
result Rich, human-understandable explanations for transfer learning.
Unified framework to bridge human and LLM judgments.
problem Systematic discrepancies between human and LLM evaluations.
method Latent human preference score and linear transformations of covariates.
result Higher agreement with human ratings and exposure of systematic gaps.
Paper proposes M2H-GAN to improve speech theme identification.
problem Limited ASR transcripts for speech theme identification.
method Uses M2H-GAN, a GAN-based approach, to generate TRS-like ASR transcripts.
result Improves speech theme identification performance close to human levels.
Study shows various pixel p-norm measures do not match human perception of adversarial attacks.
problem Understanding human perception of adversarial attacks on image classification systems.
method Performed a behavioral study comparing different p-norm measures and alternative metrics.
result Human perception of adversarial attacks does not align with pixel p-norm measures and other metrics.
Information systems experience an ever-growing volume of unstructured data, particularly in the form of textual materials. This represents a rich source of information from which one can create value for people, organizations and businesses. For instance, recommender systems can benefit from automatically understanding…
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.
A framework helps reinforcement learning agents understand and decompose tasks from human demonstrations.
problem Sparse-reward tasks where demonstrations are used as sources of causal knowledge.
method Develops causal models through observation and reasons from this knowledge to decompose tasks.
result A basic implementation of Reasoning from Demonstration (RfD) is effective in sparse-reward tasks.
Agents trained to play with themselves fail when paired with humans, suggesting the need for human-aware learning.
problem Current AI agents trained to play with themselves fail to coordinate effectively with humans.
method Introduced a simple Overcooked game environment and trained agents via self-play and population-based training. Evaluated performance against a human model.
result Agents trained to play with themselves perform poorly when paired with a human model, highlighting the need for human-aware learning.
TraLFM models human mobility patterns from traffic trajectories.
problem Understanding human mobility patterns from traffic data.
method Latent factor modeling of sequential, personal, and temporal factors.
result TraLFM significantly outperforms state-of-the-art methods in latent factor analysis and next location prediction.
AlphaZero reveals new chess concepts learnable by top experts.
problem Extracting and understanding hidden knowledge from AI systems.
method Proposed method to extract new chess concepts from AlphaZero.
result Top chess grandmasters show improvements in learning new concepts.
Quantum mechanics models human perception and decision-making, offering a new approach to understanding social dynamics.
problem Understanding the complex interactions between individuals and groups in social networks.
method Developed a simple computational code based on quantum mechanics principles to model human perception and decision-making.
result Quantum-inspired models can help explain differences in individual and group behavior.
Paper identifies problematic baselines in Shapley value explanations and proposes a reweighting mechanism.
problem Identifying and addressing the suboptimality of baselines in Shapley value feature importance analysis.
method Analyzed suboptimality of baselines, identified problematic baseline, generalized uninformativeness, and designed a reweighting mechanism.
result Proposed uncertainty-based reweighting mechanism effectively accelerates computation and improves explanation quality.
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 uses chatbot to understand users' needs for ML model explanations.
problem Lack of understanding of user needs for model explanations.
method Developed a conversational system (dr_ant) to collect user questions about a machine learning model trained on Titanic data.
result Collected a corpus of 1000+ dialogues to identify common user questions.
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.
Survey of mobility studies using mobile phone data.
problem Understanding human mobility patterns.
method Data Science techniques applied to mobile phone datasets.
result Applications in urban planning, data traffic prediction, etc.
DGDS uses documents to center conversations, promising broader AI understanding.
problem DS classification by function is insufficient for complex conversations.
method Classify DS based on document grounding, analyzing classification, architecture, datasets, and models.
result DGDS can better represent current DS development trends and future AI understanding.
ACI converts call center conversations into actionable data.
problem Real-time spoken language understanding for call center conversations.
method Combines speech recognition, entity and intent recognition, and a business rules engine.
result ACI converts live audio into structured events for real-time supervision and assistance.
IRL models human risk decisions based on past outcomes.
problem Understanding human risk decisions under risk.
method Inverse Reinforcement Learning (IRL) with features reflecting state history.
result Human reward function explains risk-prone and risk-averse decisions.
Framework analyzes RL agents' behavior to explain their strengths and weaknesses.
problem Understanding and explaining RL agents' capabilities and limitations.
method Data analysis and visualization of interaction history to extract interestingness elements.
result Visual summaries help humans correctly perceive agents' strengths and weaknesses.
New benchmark for causal reasoning from human video descriptions.
problem Lack of diversity in event types and natural language descriptions, and differences from human judgments.
method Iterative event cloze task and data augmentation techniques.
result Improved data collection efficiency and diverse causal judgments.
AlphaZero learns human chess knowledge during training.
problem Understanding how neural networks like AlphaZero acquire and represent human chess knowledge.
method Probed for a broad range of human chess concepts, analysed opening play, and investigated low-level representations.
result AlphaZero acquires and represents human chess knowledge during training.