Deep learning transforms time series into images for anomaly detection in industrial assets.
problem Detecting anomalies in time series data from industrial assets.
method Transforming time series data into image-like representations and using them as inputs for deep learning models.
result Some encodings provide competitive results for anomaly detection in industrial asset monitoring.
This paper presents a brief introduction to the key points of the Grey Machine Learning (GML) based on the kernels. The general formulation of the grey system models have been firstly summarized, and then the nonlinear extension of the grey models have been developed also with general formulations. The kernel implicit …
Proposes SAG-DBSCAN for clustering with self-adaptation.
problem Clustering analysis in data mining.
method Uses grey relational matrix and DBSCAN for clustering.
result Demonstrates superior performance compared to other methods.
Proposes a new model for equity options calibration.
problem Calibration of joint SPX/VIX options.
method Replaces fractional Brownian motion with grey Brownian motion.
result Shows potential advantages and calibration results for new model.
A framework for analyzing regularizers to ensure trustworthy theory-driven model estimation.
problem Uncertain choice of regularizers can compromise the interpretability of deep grey-box models.
method Adapting neural net architecture and training objective to analyze regularizer behavior empirically.
result Empirical analysis of regularizers helps in making a justified choice for trustworthy theory-driven model estimation.
Residual generation helps diagnose engine faults using neural networks.
problem Fault diagnosis in engines with unknown classes and limited data.
method Grey-box recurrent neural networks incorporating physical insights.
result Improved fault classification and root cause identification.
Machine learning (ML) classifiers are vulnerable to adversarial examples. An adversarial example is an input sample which is slightly modified to induce misclassification in an ML classifier. In this work, we investigate white-box and grey-box evasion attacks to an ML-based malware detector and conduct performance eval…
A new kNN imputation method improves classification performance on datasets with missing data.
problem Missing data in classification problems.
method Class weighted grey distance with MI weighting for kNN imputation.
result Improved classification performance compared to existing methods.
MOBONS optimizes complex systems with multi-objective Bayesian optimization.
problem Balancing multiple objectives in networked systems with varying model types.
method Leverages network representations and Bayesian optimization for grey-box systems.
result Efficiently optimizes general function networks with cyclic dependencies.
BOIS optimizes complex systems by combining known and unknown functions, improving efficiency.
problem Optimizing complex systems with limited structural knowledge.
method Adaptive linearization of composite functions using Gaussian Process models.
result BOIS outperforms existing grey-box methods in efficiency and effectiveness.
The main idea of this paper is to explore the possibilities of generating samples from the neural networks, mostly focusing on the colorization of the grey-scale images. I will compare the existing methods for colorization and explore the possibilities of using new generative modeling to the task of colorization. The c…
A tutorial on optimizing complex functions with partial knowledge.
problem Optimizing functions with limited or partial information.
method Grey-box Bayesian optimization, blending black-box and white-box approaches.
result Improves optimization performance by leveraging internal information.
Kernel-based machine learning approaches are gaining increasing interest for exploring and modeling large dataset in recent years. Gaussian process (GP) is one example of such kernel-based approaches, which can provide very good performance for nonlinear modeling problems. In this work, we first propose a grey-box mode…
Hybrid model combines physics and data to handle incomplete systems.
problem Incomplete physics models with missing terms.
method Combines deep grey-box models with Optimal Transport.
result Enhances incomplete physics models with superior performance.
With the widespread engineering applications ranging from artificial intelligence and big data decision-making, originally a lot of tedious financial data processing, processing and analysis have become more and more convenient and effective. This paper aims to improve the accuracy of stock price forecasting. It improv…
Study uses machine learning to detect early COVID-19 from CT images.
problem Early detection of COVID-19 from CT images.
method Machine learning methods applied to patches of CT images, feature extraction (GLCM, LDP, GLRLM, GLSZM, DWT), SVM classification.
result Best classification accuracy of 99.68% with 10-fold cross-validation and GLSZM feature extraction.
We suggest an original physical approach to describe the mechanism of market pricing. The core of our approach is to consider pricing at different time scales separately, using independent equations of motion. Such an approach leads to a pricing model that not only allows estimating the volatility of future market pric…
Improved physics-integrated generative models with noise robustness and fidelity.
problem Enhancing generative models to produce outputs that comply with physical laws and improve generalization.
method Integrating variational autoencoder with planar normalizing flow and attention mechanisms to learn latent posterior distributions and mitigate noise.
result Significant improvement in reconstruction quality and robustness against noise.
Dynamic risk assessment method for WUI fires improves upon static frameworks.
problem Static risk assessment methods fail to capture dynamic changes in WUI fire risks.
method Dynamic evaluation matrix, grey incidence analysis, optimization model.
result The proposed method effectively captures dynamic risk evolution patterns.
A new UNet variant reduces spectral artifacts in image transformations.
problem Spectral artifacts caused by traditional UNet upsampling layers.
method Introduced a Guided UNet (GUNet) architecture using a novel upsampling module.
result GUNet produces higher fidelity outputs in image transformations.
Deep learning methods have shown state of the art performance in a range of tasks from computer vision to natural language processing. However, it is well known that such systems are vulnerable to attackers who craft inputs in order to cause misclassification. The level of perturbation an attacker needs to introduce in…
Algorithm optimizes cascaded functions with known structure.
problem Optimizing a function network with known structure.
method GPN-UCB algorithm with upper confidence bounds and theoretical regret bounds.
result Near-optimal cumulative and simple regret bounds.
SFM resolves small-scale physics challenges in weather data.
problem Challenges in super-resolving small-scale details in physical sciences like weather.
method Encoding inputs to a latent base distribution, flow matching for stochastic details, adaptive noise scaling.
result SFM framework significantly outperforms existing methods.
Hybrid model outperforms benchmarks in financial forecasting.
problem Robust asset price forecasting in finance.
method Combining LSTM with Neural Levy Processes using Grey Wolf Optimizer and ANN calibration.
result Hybrid model outperforms base LSTM and other models.
Researchers disrupt Gaussian model inference to test adversarial attacks.
problem Disrupting conditional inference in multivariate Gaussian models under adversarial conditions.
method Considered white- and grey-box settings with complete and incomplete knowledge of the Gaussian distribution, respectively. Reduced to quadratic and stochastic quadratic programs. Derived structural properties for solution methods.
result Demonstrated the impact and efficacy of attacks in various applications, including real estate evaluation, interest rate estimation, and signals processing.
This study presents a new lossy image compression method that utilizes the multi-scale features of natural images. Our model consists of two networks: multi-scale lossy autoencoder and parallel multi-scale lossless coder. The multi-scale lossy autoencoder extracts the multi-scale image features to quantized variables a…
New methods merge discrete gradient fields from patches to correct errors.
problem Correctly merging partially defined discrete gradient fields from patches.
method Developed general and lean merging procedures for specific covering patterns.
result Corrected errors in merging discrete gradient fields from patches.
This paper studies the prediction of chord progressions for jazz music by relying on machine learning models. The motivation of our study comes from the recent success of neural networks for performing automatic music composition. Although high accuracies are obtained in single-step prediction scenarios, most models fa…
In this work, we present a method to compute the Kantorovich-Wasserstein distance of order one between a pair of two-dimensional histograms. Recent works in Computer Vision and Machine Learning have shown the benefits of measuring Wasserstein distances of order one between histograms with n bins, by solving a classic…
ETC improves Transformer models for long and structured inputs.
problem Scaling input length and encoding structured inputs in Transformers.
method Introduces global-local attention, relative position encodings, and CPC pre-training.
result Achieves state-of-the-art results on four natural language datasets.
We compute the condition of minimality of a G-structure for the Gray-Hervella class W4 of almost hermitian manifolds and C5 class of almost contact metric structures. We also consider C4 class by comparison with the Grey-Hervella class W4. The common feature is the ex…
Enhances quantum machine learning models using Fock states.
problem Data-embedding bottleneck in quantum machine learning.
method Photonic-based bosonic data-encoding scheme in Fock space.
result Controlled expressive power via photon number.
The condition number predicts efficient information encoding in neural units, aiding model fine-tuning.
problem Efficient information encoding in neural units for various tasks and input modalities.
method Linking the condition number to the log-volume scaling factor and entropy of the output distribution.
result High condition number indicates efficient encoding, reducing overall information transfer.
New subspace prototype flag median improves clustering on noisy data.
problem Finding robust prototypes for datasets of images and videos.
method Proposes flag median and introduces FlagIRLS algorithm for its calculation.
result Flag median is robust to outliers and improves cluster purity.
Novel neural network solves PDEs with multi-scale resolution.
problem Solving time-dependent PDEs with varying spatial and temporal scales.
method Multi-scale message passing neural network with temporal and spatial gating modules.
result Outperforms baselines on PDEs with diverse scales.
CAFLOW uses auto-regressive flows to translate images efficiently.
problem Image-to-image translation tasks.
method Transforms conditioning image into latent encodings using normalizing flows, models conditional distribution with auto-regressive distributions.
result Outperforms former conditional flow designs.
Space2Vec learns multi-scale spatial representations from grid cell insights.
problem Encoding spatial features with varying scales from GIS data.
method Proposes Space2Vec, a multi-scale representation learning model using grid cell insights.
result Space2Vec outperforms baselines in predicting POI types and image classification with geo-locations.
Object detection in point cloud data is one of the key components in computer vision systems, especially for autonomous driving applications. In this work, we present Voxel-FPN, a novel one-stage 3D object detector that utilizes raw data from LIDAR sensors only. The core framework consists of an encoder network and a c…
CNNs encode data augmentation transformations, especially in early layers.
problem Whether neural network features encode data augmentation transformations.
method Systematic approach using pre-trained vision models to predict augmentation transformations.
result Neural network features encode data augmentation transformations, especially in early layers.
Recurrent auto-encoder model summarises sequential data through an encoder structure into a fixed-length vector and then reconstructs the original sequence through the decoder structure. The summarised vector can be used to represent time series features. In this paper, we propose relaxing the dimensionality of the dec…
Randomized positional encodings boost transformer performance on longer sequences.
problem Transformers struggle with generalizing to sequences of arbitrary length.
method Introduced randomized positional encodings that simulate longer sequences and randomly select positions.
result Randomized positional encodings increase test accuracy by 12.0% on average for sequences of unseen length.
DRFormer uses dynamic tokenization and multi-scale transformer to forecast long time series.
problem Forecasting long-term time series data across diverse scales.
method Dynamic tokenizer, multi-scale transformer, dynamic sparse learning, rotary position encoding.
result DRFormer outperforms existing methods in forecasting accuracy.
Method analyzes large-scale network data to detect communication pattern shifts.
problem Analyzing large-scale time-series network data is challenging.
method Temporal encoder embedding method using ground-truth or estimated vertex labels.
result Detects communication pattern shifts across all levels of network structure.
New estimator for digital options using path splitting and MLMC.
problem Estimating digital options with stochastic differential equations.
method Repeated path splitting, Multilevel Monte Carlo (MLMC).
result Estimator complexity similar to MLMC for Lipschitz payoffs.
Regularized target encoding beats traditional methods for high cardinality features in ML.
problem Efficiently encoding high cardinality categorical variables for ML algorithms.
method Regularized target encoding compared to traditional encodings like integer and one-hot encoding.
result Regularized target encoding consistently provided the best results in a large-scale benchmark experiment.
Spectral analysis of neighborhood graphs is one of the most widely used techniques for exploratory data analysis, with applications ranging from machine learning to social sciences. In such applications, it is typical to first encode relationships between the data samples using an appropriate similarity function. Popul…
We propose a probabilistic graphical model realizing a minimal encoding of real variables dependencies based on possibly incomplete observation and an empirical cumulative distribution function per variable. The target application is a large scale partially observed system, like e.g. a traffic network, where a small pr…
We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one. Furthermore, rather than directly producing the representation, we learn a neural update rule resembling functional gra…