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.
New tools explain FRF model predictions in high-dimensional ECG data.
In the era of big data, it is desired to develop efficient machine learning algorithms to tackle massive data challenges such as storage bottleneck, algorithmic scalability, and interpretability. In this paper, we develop a novel efficient classification algorithm, called fast polynomial kernel classification (FPC), to…
We present DeepFPC, a novel deep neural network designed by unfolding the iterations of the fixed-point continuation algorithm with one-sided l1-norm (FPC-l1), which has been proposed for solving the 1-bit compressed sensing problem. The network architecture resembles that of deep residual learning and incorporates pri…
The advance of modern sensor technologies enables collection of multi-stream longitudinal data where multiple signals from different units are collected in real-time. In this article, we present a non-parametric approach to predict the evolution of multi-stream longitudinal data for an in-service unit through borrowing…
CADO optimizes heatmap-based solvers for cost minimization, overcoming performance limitations.
Deep neural network models have recently draw lots of attention, as it consistently produce impressive results in many computer vision tasks such as image classification, object detection, etc. However, interpreting such model and show the reason why it performs quite well becomes a challenging question. In this paper,…
A method for camera calibration using heatmap regression for fisheye images.
Study evaluates saliency maps on artificial data with different backgrounds.
Cephalometric tracing method is usually used in orthodontic diagnosis and treatment planning. In this paper, we propose a deep learning based framework to automatically detect anatomical landmarks in cephalometric X-ray images. We train the deep encoder-decoder for landmark detection, and combine global landmark config…
FCDD explains deep anomaly detection by mapping anomalies away and providing heatmap explanations.
Background: In cognitive neuroscience the potential of Deep Neural Networks (DNNs) for solving complex classification tasks is yet to be fully exploited. The most limiting factor is that DNNs as notorious 'black boxes' do not provide insight into neurophysiological phenomena underlying a decision. Layer-wise Relevance …
cGAP visualizes high-dimensional categorical data with interpretable geometric structure.
cGAP visualizes high-dimensional categorical data with interpretable geometric structure.
DPERC efficiently estimates covariance matrices for mixed data with missing values.
Paper evaluates CNN-based facial landmark detection methods.
Unstructured data from diverse sources, such as social media and aerial imagery, can provide valuable up-to-date information for intelligent situation assessment. Mining these different information sources could bring major benefits to applications such as situation awareness in disaster zones and mapping the spread of…
Paper proposes model to assess financial risk of grid-ignited wildfires.
We improve neural network explainability by bypassing batch normalization.
This paper introduces a novel deep learning framework for image animation. Given an input image with a target object and a driving video sequence depicting a moving object, our framework generates a video in which the target object is animated according to the driving sequence. This is achieved through a deep architect…
Proposes AtCoR for predicting bike station usage, improving station network reconfiguration.
Proposes a new method for explaining deep CNNs used in MRI-based AD diagnosis.
MCD offers a complete model understanding for high-stake decisions.
Ball trajectory data are one of the most fundamental and useful information in the evaluation of players' performance and analysis of game strategies. Although vision-based object tracking techniques have been developed to analyze sport competition videos, it is still challenging to recognize and position a high-speed …
Satellite images improve real-estate price predictions.
Simple aggregation of multiple methods defends against adversarial attacks on neural networks.
Current XAI research lacks solid foundations and clear goals.
Glare is a phenomenon that occurs when the scene has a reflection of a light source or has one in it. This luminescence can hide useful information from the image, making text recognition virtually impossible. In this paper, we propose an approach to detect glare in images taken by users via mobile devices. Our method …
In most agent-based simulators, pedestrians navigate from origins to destinations. Consequently, destinations are essential input parameters to the simulation. While many other relevant parameters as positions, speeds and densities can be obtained from sensors, like cameras, destinations cannot be observed directly. Ou…
Neural nets predict user attention from mouse movements.
This paper focuses on the problem of explaining predictions of psychological attributes such as attractiveness, happiness, confidence and intelligence from face photographs using deep neural networks. Since psychological attribute datasets typically suffer from small sample sizes, we apply transfer learning with two ba…
Applying deep learning methods to mammography assessment has remained a challenging topic. Dense noise with sparse expressions, mega-pixel raw data resolution, lack of diverse examples have all been factors affecting performance. The lack of pixel-level ground truths have especially limited segmentation methods in push…
Humans take advantage of real world symmetries for various tasks, yet capturing their superb symmetry perception mechanism with a computational model remains elusive. Motivated by a new study demonstrating the extremely high inter-person accuracy of human perceived symmetries in the wild, we have constructed the first …
An approach to utilize recent advances in deep generative models for anomaly detection in a granular (continuous) sense on a real-world image dataset with quality issues is detailed using recent normalizing flow models, with implications in many other applications/domains/data types. The approach is completely unsuperv…
The paper uses DNN for electricity price forecasting and XAI for understanding the factors.
A new matrix factorization method for high-dimensional data.
New method discovers concepts in hidden feature layers using sparse subspace clustering.
Unsupervised learning of time series data, also known as temporal clustering, is a challenging problem in machine learning. Here we propose a novel algorithm, Deep Temporal Clustering (DTC), to naturally integrate dimensionality reduction and temporal clustering into a single end-to-end learning framework, fully unsupe…
New approach predicts event probabilities for better event detection.
Various works have already showed that common shocks and cross-country financial linkages caused the banking systems of several countries to be highly interconnected with the result that during bad times, banking crises may arise simultaneously in different countries. Our aim is to provide further evidence on the topic…
Wavelet Attribution Method (WAM) improves feature attribution for deep models.
Proposes a novel anomaly detection method for echocardiogram videos.
URT layer improves few-shot image classification across diverse domains.
XLabel tool reduces medical experts' workload by 40% and explains its decisions.
New framework quantifies uncertainties in neural network explanations.
A neural network improves DOA estimation from a single snapshot.
A new method for spotting symbols in CAD images reduces annotation costs and improves accuracy.
Chronos models improve financial forecasting by integrating multivariate data.
In this paper, we identify an interesting kind of error in the output of Unsupervised Neural Machine Translation (UNMT) systems like \textit{Undreamt}(footnote). We refer to this error type as \textit{Scrambled Translation problem}. We observe that UNMT models which use \textit{word shuffle} noise (as in case of Undrea…