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.
DCR improves interpretability of concept-based models by using neural networks to build rule structures.
We developed a caching method to speed up concept learning in complex knowledge bases.
CREAM models enable concept-grounded predictions and interpretability.
This work identifies and mitigates reasoning shortcuts in Neuro-Symbolic models.
Unified model learns concepts across domains like left and right.
Neurosymbolic predictors fail to model uncertainty under independence assumption.
More than 50 years ago Bongard introduced 100 visual concept learning problems as a testbed for intelligent vision systems. These problems are now known as Bongard problems. Although they are well known in the cognitive science and AI communities only moderate progress has been made towards building systems that can so…
Automated extraction of concepts from patient clinical records is an essential facilitator of clinical research. For this reason, the 2010 i2b2/VA Natural Language Processing Challenges for Clinical Records introduced a concept extraction task aimed at identifying and classifying concepts into predefined categories (i.…
Generative concept representations have three major advantages over discriminative ones: they can represent uncertainty, they support integration of learning and reasoning, and they are good for unsupervised and semi-supervised learning. We discuss probabilistic and generative deep learning, which generative concept re…
MCD offers a complete model understanding for high-stake decisions.
Geometric framework detects concept frustration between human concepts and machine representations.
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…
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…
We consider the problem of a neural network being requested to classify images (or other inputs) without making implicit use of a "protected concept", that is a concept that should not play any role in the decision of the network. Typically these concepts include information such as gender or race, or other contextual …
Look-ahead reasoning helps predict strategic user behavior on learning platforms.
Without relevant human priors, neural networks may learn uninterpretable features. We propose Dynamics of Attention for Focus Transition (DAFT) as a human prior for machine reasoning. DAFT is a novel method that regularizes attention-based reasoning by modelling it as a continuous dynamical system using neural ordinary…
Debias concept-based explanations by removing confounding information.
Proposes CLRS benchmark to evaluate algorithmic reasoning.
Ontology learning is a critical task in industry, dealing with identifying and extracting concepts captured in text data such that these concepts can be used in different tasks, e.g. information retrieval. Ontology learning is non-trivial due to several reasons with limited amount of prior research work that automatica…
Paper refines royalty determination using Bayesian methods.
PCBM improves neural network generalization by partially observing concepts.
MXGNet tackles visual reasoning tasks using graph neural networks.
Interpretable ML methods for better decision-making with explanations.
VCML learns concepts and metaconcepts from images and questions.
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…
Attention mechanisms have been boosting the performance of deep learning models on a wide range of applications, ranging from speech understanding to program induction. However, despite experiments from psychology which suggest that attention plays an essential role in visual reasoning, the full potential of attention …
The concept of explainability is envisioned to satisfy society's demands for transparency on machine learning decisions. The concept is simple: like humans, algorithms should explain the rationale behind their decisions so that their fairness can be assessed. While this approach is promising in a local context (e.g. to…
AGENTICAITA uses AI agents to autonomously trade markets without human intervention.
Like many problems in AI in their general form, supervised learning is computationally intractable. We hypothesize that an important reason humans can learn highly complex and varied concepts, in spite of the computational difficulty, is that they benefit tremendously from experienced and insightful teachers. This pape…
COCA refactors training data to identify and erase unsafe concepts in LLMs.
COMET learns concepts for few-shot learning, improving performance.
This work abstracts deep neural networks into concept graphs for better interpretability in medical tasks.
New approach extracts AI model representations for steering and monitoring.
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…
Study clarifies Bayesian generalization error in CBM for 3-layered linear neural networks.
COLEP improves robustness of conformal prediction via probabilistic circuits.
Strict partial order is a mathematical structure commonly seen in relational data. One obstacle to extracting such type of relations at scale is the lack of large-scale labels for building effective data-driven solutions. We develop an active learning framework for mining such relations subject to a strict order. Our a…
The problem of detecting terms that can be interesting to the advertiser is considered. If a company has already bought some advertising terms which describe certain services, it is reasonable to find out the terms bought by competing companies. A part of them can be recommended as future advertising terms to the compa…
New approach uses neural networks to learn program structure and parameters.
Computer science scans LLMs to understand and manipulate their economic forecasts.
This paper expresses the structure of artificial neural network (ANN) as a functional form, using the activation integral concept derived from the activation function. In this way, the structure of ANN can be represented by a simple function, and it is possible to find the mathematical solutions of ANN. Thus, it can be…
Economic systems are similar with physic systems for their large number of individuals and the exist of equilibrium. In this paper, we present a model applying the equilibrium statistical model in economic systems. Consistent with statistical physics, we define a series of concepts, such as economic temperature, econom…
Optimizes explanations for better listener understanding.
We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving complex tasks, typically in an unsupervised or weakly-supervised setting. DRNets exploit problem structure and prior knowledge by tightly combining logic and constraint reasoning with stochastic…
Sequence models quantify uncertainty over latent concepts.
Deep learning skin lesion classifier explained using CAVs.
The paper connects higher order risk measures and stochastic dominance, showing their equivalence and integrating them with optimization.
EXOC framework uses auxiliary variables for counterfactual fairness in machine learning.