Joint probability distributions offer a wide range of highpotential applications in engineering, science, and technology (Chater et al., 2006; Griffiths et al., 2008; Knill & Pouget, 2004). Besides families of continuous distributions, introducing strong independence assumptions that must be probabilistic graphical models (PGMs), such as Bayesian known prior to learning and may turn out to be too great networks and Markov random fields (Koller & Friedman, simplifications of a model to be of practical use (Besag, 2009), are the de-facto standard in probabilistic knowledge 1975; Jain, 2012). As a simple example, consider a probability representation. They provide graph-based languages to space X, Y, C of two numeric variables, X and Y, model dependencies and independencies of variables, and and one symbolic variable C, dom(C) = {Red, Blue} as local joint or conditional distributions that quantify the statistical illustrated in Figures 1a and 1b. Let the symbolic values Red dependencies. However, the practical applicability of and Blue demaracate two clusters that are approximately PGMs suffers from the representational and computational normally distributed.

The Gaia Data Release 3 (DR3), published in June 2022, delivers a diverse set of astrometric, photometric, and spectroscopic measurements for more than a billion stars. The wealth and complexity of the data makes traditional approaches for estimating stellar parameters for the full Gaia dataset almost prohibitive. We have explored different supervised learning methods for extracting basic stellar parameters as well as distances and line-of-sight extinctions, given spectro-photo-astrometric data (including also the new Gaia XP spectra). For training we use an enhanced high-quality dataset compiled from Gaia DR3 and ground-based spectroscopic survey data covering the whole sky and all Galactic components. We show that even with a simple neural-network architecture or tree-based algorithm (and in the absence of Gaia XP spectra), we succeed in predicting competitive results (compared to Bayesian isochrone fitting) down to faint magnitudes. We will present a new Gaia DR3 stellar-parameter catalogue obtained using the currently best-performing machine-learning algorithm for tabular data, XGBoost, in the near future.

Classification margins are commonly used to estimate the generalization ability of machine learning models. We present an empirical study of these margins in artificial neural networks. A global estimate of margin size is usually used in the literature. In this work, we point out seldom considered nuances regarding classification margins. Notably, we demonstrate that some types of training samples are modelled with consistently small margins while affecting generalization in different ways. By showing a link with the minimum distance to a different-target sample and the remoteness of samples from one another, we provide a plausible explanation for this observation. We support our findings with an analysis of fully-connected networks trained on noise-corrupted MNIST data, as well as convolutional networks trained on noise-corrupted CIFAR10 data.

Due to the development of data technology, feature selection plays an important role in both statistics and machine learning. High dimensional and ultra-high dimensional datasets are widely used in many fields, such as finance, image recognition, text classification, etc. Although more detailed information is provided with the increase of dimensions, the existence of a large number of redundant features weakens the generalization ability of models and increases the difficulty of data analysis (Jain et al., 2000). Thus, the efficiency of feature selection is crucial, as it focuses on choosing a small subset of informative features that contain the information of data and determine the source of the specific concerns derived from the study. In many data analyses, feature selection is a significant and frequently used dimensionality reduction technique and is often considered a key preprocessing step in data analysis for model benefits, such as interpretability, accuracy, lower computational costs, and less prone to overfitting (Sheikhpour et al., 2017; Khaire and Dhanalakshmi, 2022).

The Web is a vast virtual space where people can share their opinions, impacting all aspects of life and having implications for marketing and communication. The most up-to-date and comprehensive information can be found on social media because of how widespread and straightforward it is to post a message. Proportionately, they are regarded as a valuable resource for making precise market predictions. In particular, Twitter has developed into a potent tool for understanding user sentiment. This article examines how well tweets can influence stock symbol trends. We analyze the volume, sentiment, and mentions of the top five stock symbols in the S&P 500 index on Twitter over three months. Long Short-Term Memory, Bernoulli Na\"ive Bayes, and Random Forest were the three algorithms implemented in this process. Our study revealed a significant correlation between stock prices and Twitter sentiment.

Fuzzy C-Means (FCM) is a widely used clustering method. However, FCM and its many accelerated variants have low efficiency in the mid-to-late stage of the clustering process. In this stage, all samples are involved in the update of their non-affinity centers, and the fuzzy membership grades of the most of samples, whose assignment is unchanged, are still updated by calculating the samples-centers distances. All those lead to the algorithms converging slowly. In this paper, a new affinity filtering technique is developed to recognize a complete set of the non-affinity centers for each sample with low computations. Then, a new membership scaling technique is suggested to set the membership grades between each sample and its non-affinity centers to 0 and maintain the fuzzy membership grades for others. By integrating those two techniques, FCM based on new affinity filtering and membership scaling (AMFCM) is proposed to accelerate the whole convergence process of FCM. Many experimental results performed on synthetic and real-world data sets have shown the feasibility and efficiency of the proposed algorithm. Compared with the state-of-the-art algorithms, AMFCM is significantly faster and more effective. For example, AMFCM reduces the number of the iteration of FCM by 80% on average.

With X-ray free-electron lasers (XFELs), it is possible to determine the three-dimensional structure of noncrystalline nanoscale particles using X-ray single-particle imaging (SPI) techniques at room temperature. Classifying SPI scattering patterns, or "speckles", to extract single hits that are needed for real-time vetoing and three-dimensional reconstruction poses a challenge for high data rate facilities like European XFEL and LCLS-II-HE. Here, we introduce SpeckleNN, a unified embedding model for real-time speckle pattern classification with limited labeled examples that can scale linearly with dataset size. Trained with twin neural networks, SpeckleNN maps speckle patterns to a unified embedding vector space, where similarity is measured by Euclidean distance. We highlight its few-shot classification capability on new never-seen samples and its robust performance despite only tens of labels per classification category even in the presence of substantial missing detector areas. Without the need for excessive manual labeling or even a full detector image, our classification method offers a great solution for real-time high-throughput SPI experiments.

Federated learning (FL) is a distributed and privacy-preserving learning framework for predictive modeling with massive data generated at the edge by Internet of Things (IoT) devices. One major challenge preventing the wide adoption of FL in IoT is the pervasive power supply constraints of IoT devices due to the intensive energy consumption of battery-powered clients for local training and model updates. Low battery levels of clients eventually lead to their early dropouts from edge networks, loss of training data jeopardizing the performance of FL, and their availability to perform other designated tasks. In this paper, we propose FedLE, an energy-efficient client selection framework that enables lifespan extension of edge IoT networks. In FedLE, the clients first run for a minimum epoch to generate their local model update. The models are partially uploaded to the server for calculating similarities between each pair of clients. Clustering is performed against these client pairs to identify those with similar model distributions. In each round, low-powered clients have a lower probability of being selected, delaying the draining of their batteries. Empirical studies show that FedLE outperforms baselines on benchmark datasets and lasts more training rounds than FedAvg with battery power constraints.

Deep learning has contributed greatly to many successes in artificial intelligence in recent years. Today, it is possible to train models that have thousands of layers and hundreds of billions of parameters. Large-scale deep models have achieved great success, but the enormous computational complexity and gigantic storage requirements make it extremely difficult to implement them in real-time applications. On the other hand, the size of the dataset is still a real problem in many domains. Data are often missing, too expensive, or impossible to obtain for other reasons. Ensemble learning is partially a solution to the problem of small datasets and overfitting. However, ensemble learning in its basic version is associated with a linear increase in computational complexity. We analyzed the impact of the ensemble decision-fusion mechanism and checked various methods of sharing the decisions including voting algorithms. We used the modified knowledge distillation framework as a decision-fusion mechanism which allows in addition compressing of the entire ensemble model into a weight space of a single model. We showed that knowledge distillation can aggregate knowledge from multiple teachers in only one student model and, with the same computational complexity, obtain a better-performing model compared to a model trained in the standard manner. We have developed our own method for mimicking the responses of all teachers at the same time, simultaneously. We tested these solutions on several benchmark datasets. In the end, we presented a wide application use of the efficient multi-teacher knowledge distillation framework. In the first example, we used knowledge distillation to develop models that could automate corrosion detection on aircraft fuselage. The second example describes detection of smoke on observation cameras in order to counteract wildfires in forests.

Hamiltonian Monte Carlo (HMC) is a popular method in sampling. While there are quite a few works of studying this method on various aspects, an interesting question is how to choose its integration time to achieve acceleration. In this work, we consider accelerating the process of sampling from a distribution $\pi(x) \propto \exp(-f(x))$ via HMC via time-varying integration time. When the potential $f$ is $L$-smooth and $m$-strongly convex, i.e.\ for sampling from a log-smooth and strongly log-concave target distribution $\pi$, it is known that under a constant integration time, the number of iterations that ideal HMC takes to get an $\epsilon$ Wasserstein-2 distance to the target $\pi$ is $O( \kappa \log \frac{1}{\epsilon} )$, where $\kappa := \frac{L}{m}$ is the condition number. We propose a scheme of time-varying integration time based on the roots of Chebyshev polynomials. We show that in the case of quadratic potential $f$, i.e., when the target $\pi$ is a Gaussian distribution, ideal HMC with this choice of integration time only takes $O( \sqrt{\kappa} \log \frac{1}{\epsilon} )$ number of iterations to reach Wasserstein-2 distance less than $\epsilon$; this improvement on the dependence on condition number is akin to acceleration in optimization. The design and analysis of HMC with the proposed integration time is built on the tools of Chebyshev polynomials. Experiments find the advantage of adopting our scheme of time-varying integration time even for sampling from distributions with smooth strongly convex potentials that are not quadratic.