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.
The paper supports task classification from eye movements, achieving 95.4% accuracy.
This article reports on an investigation of the use of convolutional neural networks to predict the visual attention of chess players. The visual attention model described in this article has been created to generate saliency maps that capture hierarchical and spatial features of chessboard, in order to predict the pro…
We propose to model the fixation locations of the human eye when observing a still image by a Markovian point process in R 2 . Our approach is data driven using k-means clustering of the fixation locations to identify distinct salient regions of the image, which in turn correspond to the states of our Markov chain. Bay…
Research studies have shown that a large proportion of hazards remain unrecognized, which expose construction workers to unanticipated safety risks. Recent studies have also found that a strong correlation exists between viewing patterns of workers, captured using eye-tracking devices, and their hazard recognition perf…
Automated method selects eye tracking variables for categorization tasks.
Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition. However, as we show in this paper, these networks are highly overparameterized for the task of fixation prediction. We first present a simple yet principled greedy…
Novel CNN-based gaze scanpath comparison distinguishes experts from novices in dental radiograph interpretation.
Eye Movement analysis with Hidden Markov Models (EMHMM) is a method for modeling eye fixation sequences using hidden Markov models (HMMs). In this report, we run a simulation study to investigate the estimation error for learning HMMs with variational Bayesian inference, with respect to the number of sequences and the …
We present a dynamical many-body theory of money in which the value of money is a time dependent ``strategic variable'' that is chosen by the individual agents. The value of money in equilibrium is not fixed by the equations, and thus represents a continuous symmetry. The dynamics breaks this continuous symmetry by fix…
We study the problem of inferring readers' identities and estimating their level of text comprehension from observations of their eye movements during reading. We develop a generative model of individual gaze patterns (scanpaths) that makes use of lexical features of the fixated words. Using this generative model, we d…
An important problem for HCI researchers is to estimate the parameter values of a cognitive model from behavioral data. This is a difficult problem, because of the substantial complexity and variety in human behavioral strategies. We report an investigation into a new approach using approximate Bayesian computation (AB…
regvis.net offers a visual survey of regulatory visualization.
New benchmarks focus on LLM risk in finance, not just accuracy.
We study how to leverage off-the-shelf visual and linguistic data to cope with out-of-vocabulary answers in visual question answering task. Existing large-scale visual datasets with annotations such as image class labels, bounding boxes and region descriptions are good sources for learning rich and diverse visual conce…
The paper characterizes brain states and transitions using functional MRI data.
Proposes a spectral method to assess and combine multiple data visualizations.
To convey neural network architectures in publications, appropriate visualizations are of great importance. While most current deep learning papers contain such visualizations, these are usually handcrafted just before publication, which results in a lack of a common visual grammar, significant time investment, errors,…
AV-CPL uses continuous pseudo-labels for AVSR combining labeled and unlabeled data.
Visualizes futures markets using particle physics tools.
New report on machine learning visualization techniques and trends.
The abstract discusses how humans use visualizations in machine learning.
IANN visualizes all input variables effects simultaneously.
Consensus dimension reduction combines multiple visualizations to identify shared patterns.
Visualizes deep generative models for drug design.
This paper discusses the role of risk communication in macroprudential oversight and of visualization in risk communication. Beyond the soar in data availability and precision, the transition from firm-centric to system-wide supervision imposes vast data needs. Moreover, except for internal communication as in any orga…
Paper establishes baselines for offline RL from visual observations.
WAPPO optimizes feature distributions for better visual transfer in RL.
Develops piecewise visual, linearly connected metrics on group boundaries.
We introduce the notion of the visual core of a hyperbolic 3-manifold N and explore its basic properties. The visual core can be thought of as a harmonic analysis analogue of the convex core. We investigate circumstances in which the visual core of a cover N' of N embeds under the covering map from N' to N. We apply th…
A novel method visualizes higher-dimensional spaces using hyperbolic geometry.
Ray marching method visualizes flat surfaces efficiently.
Pretrained model improves visual dialog performance.
We present GraphTSNE, a novel visualization technique for graph-structured data based on t-SNE. The growing interest in graph-structured data increases the importance of gaining human insight into such datasets by means of visualization. Among the most popular visualization techniques, classical t-SNE is not suitable o…
Adversarial attacks can manipulate ML-aided visualizations, tricking analysts.
DEN creates interpretable visualizations using Siamese networks.
Explains visual metrics on hyperbolic space boundaries.
Developing a visual platform for faster astronomical source cataloging.
Croke and Kleiner constructed two homeomorphic locally CAT(0) complexes whose universal covers have visual boundaries that are not homeomorphic. We construct two homeomorphic locally CAT(0) complexes so that the visual boundary of one universal cover contains a nonplanar graph, while the visual boundary of the other do…
As machine learning becomes more pervasive, there is an urgent need for interpretable explanations of predictive models. Prior work has developed effective methods for visualizing global model behavior, as well as generating local (instance-specific) explanations. However, relatively little work has addressed regional …
Visual design improves financial data classification accuracy.
Neural coding is one of the central questions in systems neuroscience for understanding how the brain processes stimulus from the environment, moreover, it is also a cornerstone for designing algorithms of brain-machine interface, where decoding incoming stimulus is highly demanded for better performance of physical de…
System helps scientists visualize deep learning model of x-ray images.
GTSNE improves data visualization for high-dimensional data.
UN-AVOIDS visualizes and detects anomalies without needing labeled data.
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual de…
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent success of convolutional neural networks (CNNs) in SE, we propose an audio-visual de…
Method generates visual explanations for similarity models without classification.
A neural network visualizes data structure and concepts.