Programmatic Motion Concepts learn human actions from paired videos.
problem Learning motion concepts from paired video and action sequences.
method Semi-supervised learning architecture for hierarchical motion representation.
result Outperforms established baselines, especially in small data settings.
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.
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.
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.
VICE embeds concepts in a vector space using human data.
problem Developing numerical models for mental representations of object concepts.
method Variational Interpretable Concept Embeddings (VICE) using variational inference and triplet odd-one-out task data.
result VICE outperforms SPoSE at predicting human behavior and provides more reproducible object representations.
Examines parallels between human subjects and texts for causal inference.
problem Ambiguity and fallacies in causal inference using textual data.
method Two strategies: shifting from traits to perceptions and from concepts to parts.
result Highlights the importance of clarifying fundamental concepts.
We consider the problem of explaining the decisions of deep neural networks for image recognition in terms of human-recognizable visual concepts. In particular, given a test set of images, we aim to explain each classification in terms of a small number of image regions, or activation maps, which have been associated w…
In an attempt to gather a deeper understanding of how convolutional neural networks (CNNs) reason about human-understandable concepts, we present a method to infer labeled concept data from hidden layer activations and interpret the concepts through a shallow decision tree. The decision tree can provide information abo…
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.
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.
New methods identify concepts in trained embeddings reliably without human labels.
problem Identifying interpretable concepts in trained embedding spaces without human labels.
method Explicitly connecting concept discovery to PCA and ICA, proposing novel approaches for dependent concepts.
result Proven methods outperform competitors on a variety of experiments, achieving up to 29% better alignment with ground truth.
Bayesian model predicts sequences better than LSTMs by identifying underlying rules.
problem Current RNNs struggle to generalize from limited training data and identify underlying rules in sequences.
method Bayesian model that learns underlying concepts from sequences and generalizes to new data.
result Bayesian model predicts sequences better than traditional LSTMs.
In this paper we propose and study the novel problem of explaining node embeddings by finding embedded human interpretable subspaces in already trained unsupervised node representation embeddings. We use an external knowledge base that is organized as a taxonomy of human-understandable concepts over entities as a guide…
New method learns interpretable concepts from user feedback for high-dimensional data.
problem Lack of interpretable concepts in machine learning models trained on high-dimensional tabular data.
method Proposes a method for learning transparent concept definitions from user labeling of concept features, not instances.
result Demonstrates more efficient learning of aligned concept definitions from user feedback compared to alternative transparent approaches.
The growth of the modern knowledge-based economy is becoming less and less dependent on tangible assets and more on intangible ones. In this context, the role of human capital in the value creation process has become central. Despite the large amount of scientific work on human capital phenomena, little research has re…
Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explanation methods provide explanations through feature importance scores, which identify features that are important for each individual input. …
COMET learns concepts for few-shot learning, improving performance.
problem Few-shot learning challenges in machine learning.
method Meta-learning with human-interpretable concept dimensions.
result Significant improvement in 1-shot learning tasks.
DCR improves interpretability of concept-based models by using neural networks to build rule structures.
problem Inability of concept-based models to provide transparent decision processes.
method DCR uses neural networks to build syntactic rule structures using concept embeddings and executes these rules on concept truth degrees.
result DCR improves interpretability by up to 25% on challenging benchmarks and discovers meaningful logic rules.
New method extracts biological concepts from cell microscopy images.
problem Extracting meaningful concepts from vision foundation models trained on cell microscopy images.
method Sparse dictionary learning (DL) combined with PCA whitening pre-processing.
result Successfully retrieved biologically meaningful concepts like cell types and genetic perturbations.
The concept of progress has characterized human society from millennia. However, this concept is elusive and too often given for certain. The goal of this paper is to suggest a general definition of human progress that satisfies, whenever possible the conditions of independence, generality, epistemological applicabilit…
This paper is a tutorial on Formal Concept Analysis (FCA) and its applications. FCA is an applied branch of Lattice Theory, a mathematical discipline which enables formalisation of concepts as basic units of human thinking and analysing data in the object-attribute form. Originated in early 80s, during the last three d…
Artificial intelligence (AI) is intrinsically data-driven. It calls for the application of statistical concepts through human-machine collaboration during generation of data, development of algorithms, and evaluation of results. This paper discusses how such human-machine collaboration can be approached through the sta…
CA connects visual concepts to neural network representations.
problem Global association of human interpretable concepts with neural network internals.
method Established a taxonomy for CA methods and reviewed state-of-the-art research.
result Unified understanding of CA methods and datasets.
Humans have an impressive ability to reason about new concepts and experiences from just a single example. In particular, humans have an ability for one-shot generalization: an ability to encounter a new concept, understand its structure, and then be able to generate compelling alternative variations of the concept. We…
New approach extracts AI model representations for steering and monitoring.
problem Understanding and steering AI models' internal knowledge representation.
method Feature learning advances for scalable linear concept representations.
result Concept representations enable steering and monitoring of AI models.
Predicting the outcomes of integrating Unmanned Aerial Systems (UAS) into the National Aerospace (NAS) is a complex problem which is required to be addressed by simulation studies before allowing the routine access of UAS into the NAS. This thesis focuses on providing 2D and 3D simulation frameworks using a game theore…
The technique of Formal Concept Analysis is applied to a dataset describing the traits of rodents, with the goal of identifying zoonotic disease carriers,or those species carrying infections that can spillover to cause human disease. The concepts identified among these species together provide rules-of-thumb about the …
The paper argues for a social-economic approach to AI development.
problem The current AI development overlooks social and cultural aspects of intelligence.
method A blend of economic and social concepts with computational and inferential concepts in algorithm design.
result A social-economic approach is necessary for proper AI development.
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…
New method discovers concepts in hidden feature layers using sparse subspace clustering.
problem Local attribution methods fail to identify coherent model behavior across samples.
method Sparse Subspace Clustering (SSCC) for concept discovery.
result Empirically validated method for various image classification tasks.
Concept-driven OPE reduces variance in off-policy decision evaluation.
problem High variance in off-policy decision evaluation due to limited sample sizes.
method Integrating human-explainable concepts into OPE to reduce variance.
result Concept-based OPE estimators remain unbiased and reduce variance when concepts are known and predefined.
CAVs reveal latent concept distributions, but are vulnerable to adversarial attacks.
problem Understanding latent concept encodings in AI models.
method Probabilistic perspective on CAVs, deriving mean and covariance.
result CAVs can be adversarially manipulated, highlighting a vulnerability.
Standard deep learning systems require thousands or millions of examples to learn a concept, and cannot integrate new concepts easily. By contrast, humans have an incredible ability to do one-shot or few-shot learning. For instance, from just hearing a word used in a sentence, humans can infer a great deal about it, by…
Human explanations of high-level decisions are often expressed in terms of key concepts the decisions are based on. In this paper, we study such concept-based explainability for Deep Neural Networks (DNNs). First, we define the notion of completeness, which quantifies how sufficient a particular set of concepts is in e…
Deep learning skin lesion classifier explained using CAVs.
problem Limited acceptance of deep learning CAD systems due to opaque decision-making.
method Mapped human understandable concepts to RECOD model using CAVs.
result Classifier learns and encodes disease-related concepts in its latent representation.
Prob2Vec embeds problems for adaptive tutoring, achieving high similarity accuracy.
problem Retrieve problems with similar mathematical concepts for adaptive tutoring.
method Hierarchical problem embedding algorithm (Prob2Vec) combining abstraction and embedding steps.
result 96.88% accuracy on problem similarity test, significantly outperforming state-of-the-art sentence embedding methods.
Unified approach to learn interpretable concepts from data.
problem Building interpretable machine learning models and highly-performing foundation models.
method Relating causal representation learning and foundation models, defining concepts and proving their recoverability.
result Provable recovery of human-interpretable concepts from diverse data.
Learning preferences implicit in the choices humans make is a well studied problem in both economics and computer science. However, most work makes the assumption that humans are acting (noisily) optimally with respect to their preferences. Such approaches can fail when people are themselves learning about what they wa…
Concept bottleneck models enable concept manipulation for model interpretation.
problem Training models to directly predict labels without intermediate concepts.
method Train models to predict intermediate concepts at training time, then use these concepts to predict labels.
result Concept bottleneck models achieve competitive accuracy with standard models while enabling concept manipulation.
INVERT connects neural representations to human-understandable concepts.
problem Lack of understanding and statistical significance in existing explainability methods.
method Inverse Recognition (INVERT) approach that connects learned representations to human-understandable concepts.
result INVERT provides interpretable metrics and statistical significance for representation alignment.
After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning concepts efficiently in a continual learning setting remains an open challenge for curr…
NeuroQuery synthesizes brain mapping evidence across diverse concepts.
problem Lack of comprehensive meta-analysis of human brain mapping across different mental processes and mechanisms.
method A multivariate model that predicts the spatial distribution of neurological observations given text describing an experiment, cognitive process, or disease.
result Captures relationships and neural correlates of 7,547 neuroscience terms across 13,459 neuroimaging publications.
The study identifies latent concepts from diverse observations without assuming specific models.
problem Lack of general theoretical support for concept learning.
method Develops a nonparametric framework for identifying latent concepts from multiple classes of observations.
result Correctness guarantees for concept identification without parametric assumptions.
New models handle survival analysis with concept-based learning.
problem Survival analysis tasks involving event times with censored data.
method SurvCBM and SurvRCM models integrating concept-based learning with survival analysis.
result SurvCBM outperforms traditional survival models in numerical experiments.
VCML learns concepts and metaconcepts from images and questions.
problem Learning concepts and metaconcepts from visual data.
method Bidirectional connection between visual concepts and metaconcepts.
result VCML can generalize from limited data and noisy inputs.
A new framework for interpretable models using sparse linear layers.
problem Performance degradation and lower interpretability in concept bottleneck models.
method Contrastive Language Image models and a single sparse linear layer with Bayesian inference.
result Our framework outperforms recent CBM approaches in accuracy and concept sparsity.
This work improves interpretability in deep learning models by introducing a two-level concept discovery framework.
problem High complexity and lack of interpretability in deep learning models, especially for safety-critical tasks.
method Concept Bottleneck Models (CBMs) framework combining vision-language models and data-driven coarse-to-fine concept selection.
result The proposed framework outperforms recent CBM approaches and provides a principled interpretability.
The paper benchmarks data stream classifiers for human activity recognition on connected devices.
problem Challenges in human activity recognition on connected devices, particularly high memory consumption and low F1 scores.
method Evaluation of five stream classification algorithms on real and synthetic datasets, measuring both performance and resource consumption.
result HT and MF classifiers show superior performance and resilience to concept drift compared to other algorithms.