Many promising applications of supervised machine learning face hurdles in the acquisition of labeled data in sufficient quantity and quality, creating an expensive bottleneck. To overcome such limitations, techniques that do not depend on ground truth labels have been studied, including weak supervision and generative modeling. While these techniques would seem to be usable in concert, improving one another, how to build an interface between them is not well-understood. In this work, we propose a model fusing programmatic weak supervision and generative adversarial networks and provide theoretical justification motivating this fusion. The proposed approach captures discrete latent variables in the data alongside the weak supervision derived label estimate. Alignment of the two allows for better modeling of sample-dependent accuracies of the weak supervision sources, improving the estimate of unobserved labels. It is the first approach to enable data augmentation through weakly supervised synthetic images and pseudolabels. Additionally, its learned latent variables can be inspected qualitatively. The model outperforms baseline weak supervision label models on a number of multiclass image classification datasets, improves the quality of generated images, and further improves end-model performance through data augmentation with synthetic samples. How can we get the most out of data when we do not have ground truth labels? Two prominent paradigms operate in this setting. First, programmatic weak supervision frameworks use weak sources of training signal to train downstream supervised models, without needing access to groundtruth labels (Riedel et al., 2010; Ratner et al., 2016; Dehghani et al., 2017; Lang & Poon, 2021). Second, generative models enable learning data distributions which can benefit downstream tasks, e.g. Intuitively, these two paradigms should complement each other, as each can be thought of as a different approach to extracting structure from unlabeled data. However, to date there is no simple way to combine them. Fusing generative models with weak supervision holds substantial promise. For example, it could yield large reductions in data acquisition costs for training complex models. Programmatic weak supervision replaces the need for manual annotations by applying so-called labeling functions to unlabeled data, producing weak labels that are combined into a pseudolabel for each sample.

Adversarial reprogramming allows repurposing a machine-learning model to perform a different task. For example, a model trained to recognize animals can be reprogrammed to recognize digits by embedding an adversarial program in the digit images provided as input. Recent work has shown that adversarial reprogramming may not only be used to abuse machine-learning models provided as a service, but also beneficially, to improve transfer learning when training data is scarce. However, the factors affecting its success are still largely unexplained. In this work, we develop a first-order linear model of adversarial reprogramming to show that its success inherently depends on the size of the average input gradient, which grows when input gradients are more aligned, and when inputs have higher dimensionality. The results of our experimental analysis, involving fourteen distinct reprogramming tasks, show that the above factors are correlated with the success and the failure of adversarial reprogramming.

Recently, graph neural networks (GNNs) have been successfully applied to predicting molecular properties, which is one of the most classical cheminformatics tasks with various applications. Despite their effectiveness, we empirically observe that training a single GNN model for diverse molecules with distinct structural patterns limits its prediction performance. In this paper, motivated by this observation, we propose TopExpert to leverage topology-specific prediction models (referred to as experts), each of which is responsible for each molecular group sharing similar topological semantics. That is, each expert learns topology-specific discriminative features while being trained with its corresponding topological group. To tackle the key challenge of grouping molecules by their topological patterns, we introduce a clustering-based gating module that assigns an input molecule into one of the clusters and further optimizes the gating module with two different types of self-supervision: topological semantics induced by GNNs and molecular scaffolds, respectively. Extensive experiments demonstrate that TopExpert has boosted the performance for molecular property prediction and also achieved better generalization for new molecules with unseen scaffolds than baselines. The code is available at https://github.com/kimsu55/ToxExpert.

Predictive analytics aims to build machine learning models to predict behavior patterns and use predictions to guide decision-making. Predictive analytics is human involved, thus the machine learning model is preferred to be interpretable. In literature, Generalized Additive Model (GAM) is a standard for interpretability. However, due to the one-to-many and many-to-one phenomena which appear commonly in real-world scenarios, existing GAMs have limitations to serve predictive analytics in terms of both accuracy and training efficiency. In this paper, we propose FXAM (Fast and eXplainable Additive Model), a unified and fast interpretable model for predictive analytics. FXAM extends GAM's modeling capability with a unified additive model for numerical, categorical, and temporal features. FXAM conducts a novel training procedure called Three-Stage Iteration (TSI). TSI corresponds to learning over numerical, categorical, and temporal features respectively. Each stage learns a local optimum by fixing the parameters of other stages. We design joint learning over categorical features and partial learning over temporal features to achieve high accuracy and training efficiency. We prove that TSI is guaranteed to converge to the global optimum. We further propose a set of optimization techniques to speed up FXAM's training algorithm to meet the needs of interactive analysis. Thorough evaluations conducted on diverse data sets verify that FXAM significantly outperforms existing GAMs in terms of training speed, and modeling categorical and temporal features. In terms of interpretability, we compare FXAM with the typical post-hoc approach XGBoost+SHAP on two real-world scenarios, which shows the superiority of FXAM's inherent interpretability for predictive analytics.

Becoming a machine learning engineer requires a combination of skills and knowledge in various areas such as mathematics, programming, data analysis, and machine learning algorithms. Learn the basics of mathematics and statistics: Machine learning requires a strong foundation in mathematics and statistics. You should be familiar with calculus, linear algebra, probability, and statistics. Master a programming language: You should learn a programming language such as Python or R, which are commonly used for machine learning. You should also be familiar with data structures, algorithms, and object-oriented programming.

The epidemiological characteristics and clinical examination methods of thyroid nodules: Thyroid nodules are widespread clinically, and the incidence continues to rise worldwide, with an autopsy study estimating that 50% to 60% of adults may have thyroid nodules (1, 2). High-resolution ultrasound (US) can detect thyroid nodules in 19%- 68% (3) of randomly selected individuals, of which thyroid cancer occurs in 7% to 15% (4). Thyroid cancer is the most common endocrine malignancy in the United States (5) and the fifth most common cancer among women (6). The benign thyroid nodules without surgical indications generally do not require special treatment. In contrast, malignant thyroid nodules should be elective surgical treatment once diagnosed, and neck dissection should be performed if lymph node metastases are present. Some patients need to be treated with Iodine-131 nuclide after the operation (7) and predict the prognosis. Papillary thyroid carcinoma (PTC) is the most common pathological type of thyroid cancer. It usually has a good prognosis, but relapse patients have a poor prognosis. About 10%-15% of PTC will relapse, and recurrent PTC has aggressive characteristics such as extra-thyroid extension (ETE), invasive cell subtypes, lateral neck lymphatic metastasis, resistance to therapy, and distant metastases (8). The challenge for clinicians is to balance treatment approaches so that patients with low-risk or benign thyroid nodules are not over-treated, while patients with high-risk or malignant thyroid nodules need more aggressive therapies. Therefore, the differential diagnosis of thyroid nodules and the risk stratification are essential and helpful for the subsequent individualized treatment.

A mathematical representation of the results of the training process is a machine learning model. Machine learning is the study of various algorithms that could create a model automatically through the use and past data. A machine learning model is similar to computer software that can recognize patterns or actions based on prior knowledge or data. The learning algorithm scans the training data for patterns and then generates a machine learning (ML) model that captures those patterns. As a result, we can characterize a machine learning model as a simplified version of a concept or process.

Abstract-- Distributed sensor arrays capable of detecting multiple spatially distributed stimuli are considered an important element in the realisation of exteroceptive and proprioceptive soft robots. This paper expands upon the previously presented idea of decoupling the measurements of pressure and location of a local indentation from global deformation, using the overall stretch experienced by a soft capacitive e-skin. We employed machine learning methods to decouple and predict these highly coupled deformation stimuli, collecting data from a soft sensor e-skin which was then fed to a machine learning system comprising of linear regressor, gaussian process regressor, SVM and random forest classifier for stretch, force, detection and localisation respectively. We also studied how the localisation and forces are affected when two forces are applied simultaneously. Soft sensor arrays aided by appropriately chosen machine learning techniques can pave the way to e-skins capable of deciphering multi-modal stimuli in soft robots. I. INTRODUCTION Soft robots, unlike traditional, rigid-component robots commonly used in industries, are made from soft, deformable materials and are capable of adapting to the environment in a compliant manner.

Various privacy-preserving frameworks that respect the individual's privacy in the analysis of data have been developed in recent years. However, available model classes such as simple statistics or generalized linear models lack the flexibility required for a good approximation of the underlying data-generating process in practice. In this paper, we propose an algorithm for a distributed, privacy-preserving, and lossless estimation of generalized additive mixed models (GAMM) using component-wise gradient boosting (CWB). Making use of CWB allows us to reframe the GAMM estimation as a distributed fitting of base learners using the $L_2$-loss. In order to account for the heterogeneity of different data location sites, we propose a distributed version of a row-wise tensor product that allows the computation of site-specific (smooth) effects. Our adaption of CWB preserves all the important properties of the original algorithm, such as an unbiased feature selection and the feasibility to fit models in high-dimensional feature spaces, and yields equivalent model estimates as CWB on pooled data. Next to a derivation of the equivalence of both algorithms, we also showcase the efficacy of our algorithm on a distributed heart disease data set and compare it with state-of-the-art methods.

Self-paced learning has been beneficial for tasks where some initial knowledge is available, such as weakly supervised learning and domain adaptation, to select and order the training sample sequence, from easy to complex. However its applicability remains unexplored in unsupervised learning, whereby the knowledge of the task matures during training. We propose a novel HYperbolic Self-Paced model (HYSP) for learning skeletonbased action representations. HYSP adopts self-supervision: it uses data augmentations to generate two views of the same sample, and it learns by matching one (named online) to the other (the target). We propose to use hyperbolic uncertainty to determine the algorithmic learning pace, under the assumption that less uncertain samples should be more strongly driving the training, with a larger weight and pace. Hyperbolic uncertainty is a by-product of the adopted hyperbolic neural networks, it matures during training and it comes with no extra cost, compared to the established Euclidean SSL framework counterparts. When tested on three established skeleton-based action recognition datasets, HYSP outperforms the state-of-the-art on PKU-MMD I, as well as on 2 out of 3 downstream tasks on NTU-60 and NTU-120. Additionally, HYSP only uses positive pairs and bypasses therefore the complex and computationally-demanding mining procedures required for the negatives in contrastive techniques. Starting from the seminal work of Kumar et al. (2010), the machine learning community has started looking at self-paced learning, i.e. determining the ideal sample order, from easy to complex, to improve the model performance. Self-paced learning has been adopted so far for weakly-supervised learning (Liu et al., 2021; Wang et al., 2021; Sangineto et al., 2019), or where some initial knowledge is available, e.g. from a source model, in unsupervised domain adaption (Liu et al., 2021). Selfpaced approaches use the label (or pseudo-label) confidence to select easier samples and train on those first. However labels are not available in self-supervised learning (SSL) (Chen et al., 2020a; He et al., 2020; Grill et al., 2020; Chen & He, 2021), where the supervision comes from the data structure itself, i.e. from the sample embeddings.