A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Programmatic Motion Concepts learn human actions from paired videos.
AlphaZero reveals new chess concepts learnable by top experts.
Geometric framework detects concept frustration between human concepts and machine representations.
LCBM model improves image classification without human supervision.
VICE embeds concepts in a vector space using human data.
Examines parallels between human subjects and texts for causal inference.
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.
When people learn mathematical patterns or sequences, they are able to identify the concepts (or rules) underlying those patterns. Having learned the underlying concepts, humans are also able to generalize those concepts to other numbers, so far as to even identify previously unseen combinations of those rules. Current…
High-dimensional neural network manifolds misalign with human perception, causing adversarial examples.
New methods identify concepts in trained embeddings reliably without human labels.
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.
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.
DCR improves interpretability of concept-based models by using neural networks to build rule structures.
New method extracts biological concepts from cell microscopy images.
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.
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.
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.
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.
Concept-driven OPE reduces variance in off-policy decision evaluation.
CAVs reveal latent concept distributions, but are vulnerable to adversarial attacks.
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.
Prob2Vec embeds problems for adaptive tutoring, achieving high similarity accuracy.
Unified approach to learn interpretable concepts from 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.
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…
INVERT connects neural representations to human-understandable concepts.
The study identifies latent concepts from diverse observations without assuming specific models.
New models handle survival analysis with concept-based learning.
Humans reason with concepts and metaconcepts: we recognize red and green from visual input; we also understand that they describe the same property of objects (i.e., the color). In this paper, we propose the visual concept-metaconcept learner (VCML) for joint learning of concepts and metaconcepts from images and associ…
A new framework for interpretable models using sparse linear layers.
This work improves interpretability in deep learning models by introducing a two-level concept discovery framework.
The paper benchmarks data stream classifiers for human activity recognition on connected devices.
CB-SLICE identifies concept-based error slices in deep learning models.