We present a multi-modal stress dataset that uses digital job interviews to induce stress. The dataset provides multi-modal data of 40 participants including audio, video (motion capturing, facial recognition, eye tracking) as well as physiological information (photoplethysmography, electrodermal activity). In addition to that, the dataset contains time-continuous annotations for stress and occurred emotions (e.g. shame, anger, anxiety, surprise). In order to establish a baseline, five different machine learning classifiers (Support Vector Machine, K-Nearest Neighbors, Random Forest, Long-Short-Term Memory Network) have been trained and evaluated on the proposed dataset for a binary stress classification task. The best-performing classifier achieved an accuracy of 88.3% and an F1-score of 87.5%.

Out-of-distribution (OOD) inputs can compromise the performance and safety of real world machine learning systems. While many methods exist for OOD detection and work well on small scale datasets with lower resolution and few classes, few methods have been developed for large-scale OOD detection. Existing large-scale methods generally depend on maximum classification probability, such as the state-of-the-art grouped softmax method. In this work, we develop a novel approach that calculates the probability of the predicted class label based on label distributions learned during the training process. Our method performs better than current state-of-the-art methods with only a negligible increase in compute cost. We evaluate our method against contemporary methods across $14$ datasets and achieve a statistically significant improvement with respect to AUROC (84.2 vs 82.4) and AUPR (96.2 vs 93.7).

Human communication is increasingly intermixed with language generated by AI. Across chat, email, and social media, AI systems suggest words, complete sentences, or produce entire conversations. AI-generated language is often not identified as such but presented as language written by humans, raising concerns about novel forms of deception and manipulation. Here, we study how humans discern whether verbal self-presentations, one of the most personal and consequential forms of language, were generated by AI. In six experiments, participants (N = 4,600) were unable to detect self-presentations generated by state-of-the-art AI language models in professional, hospitality, and dating contexts. A computational analysis of language features shows that human judgments of AI-generated language are hindered by intuitive but flawed heuristics such as associating first-person pronouns, use of contractions, or family topics with human-written language. We experimentally demonstrate that these heuristics make human judgment of AI-generated language predictable and manipulable, allowing AI systems to produce text perceived as "more human than human." We discuss solutions, such as AI accents, to reduce the deceptive potential of language generated by AI, limiting the subversion of human intuition.

We consider the sequential decision-making problem where the mean outcome is a non-linear function of the chosen action. Compared with the linear model, two curious phenomena arise in non-linear models: first, in addition to the "learning phase" with a standard parametric rate for estimation or regret, there is an "burn-in period" with a fixed cost determined by the non-linear function; second, achieving the smallest burn-in cost requires new exploration algorithms. For a special family of non-linear functions named ridge functions in the literature, we derive upper and lower bounds on the optimal burn-in cost, and in addition, on the entire learning trajectory during the burn-in period via differential equations. In particular, a two-stage algorithm that first finds a good initial action and then treats the problem as locally linear is statistically optimal. In contrast, several classical algorithms, such as UCB and algorithms relying on regression oracles, are provably suboptimal.

Detecting out-of-distribution (OOD) data is a task that is receiving an increasing amount of research attention in the domain of deep learning for computer vision. However, the performance of detection methods is generally evaluated on the task in isolation, rather than also considering potential downstream tasks in tandem. In this work, we examine selective classification in the presence of OOD data (SCOD). That is to say, the motivation for detecting OOD samples is to reject them so their impact on the quality of predictions is reduced. We show under this task specification, that existing post-hoc methods perform quite differently compared to when evaluated only on OOD detection. This is because it is no longer an issue to conflate in-distribution (ID) data with OOD data if the ID data is going to be misclassified. However, the conflation within ID data of correct and incorrect predictions becomes undesirable. We also propose a novel method for SCOD, Softmax Information Retaining Combination (SIRC), that augments softmax-based confidence scores with feature-agnostic information such that their ability to identify OOD samples is improved without sacrificing separation between correct and incorrect ID predictions. Experiments on a wide variety of ImageNet-scale datasets and convolutional neural network architectures show that SIRC is able to consistently match or outperform the baseline for SCOD, whilst existing OOD detection methods fail to do so.

Such drawings encode the topological information, dimensions, and manufacturing requirements of a product in a unified and standard form, which can then be utilized in various engineering applications including content-based part indexing (Fonseca et al., 2005; Kasimov et al., 2015), cost estimation (Sajadfar and Ma, 2015), and process planning (Kulkarni et al., 2000). Although the underlying designs are commonly created in a vector format through digital design tools, a raster drawing is more frequently used by manufacturers due to the ease of information exchange and quality assurance. According to a survey of Japan's manufacturing industry (Mitsubishi UFJ Research & Consulting Co., 2019), 84% of the customers use 2D raster-based drawings such as PDF, paper, or fax format when placing an order for manufacturing, which results in a major impediment in the automation of the aforementioned applications due to the need for human involvement in interpreting these drawings. For a modern online platform of part manufacturing, clients often upload their designs in raster image format for better quality assurance and IP protection since the information in image drawings is noneditable. Unlike a vector format, which enables trivial digital access to all stored information through a script file, raster drawings usually require manual inspection by technicians to extract the information required for quotation and manufacturing. The inspection process includes the identification of the part shape, dimensions, and manufacturing requirements. Here, we focus on the problem of semantic segmentation of the components in raster drawings. Common mechanical engineering components consist of straight lines, arcs, and circles. Our goal is to develop an automated data-driven framework that learns to distinguish between contour shapes, dimension sets, and text at the component level.

Gaussian Processes (GPs) are expressive models for capturing signal statistics and expressing prediction uncertainty. As a result, the robotics community has gathered interest in leveraging these methods for inference, planning, and control. Unfortunately, despite providing a closed-form inference solution, GPs are non-parametric models that typically scale cubically with the dataset size, hence making them difficult to be used especially on onboard Size, Weight, and Power (SWaP) constrained aerial robots. In addition, the integration of popular libraries with GPs for different kernels is not trivial. In this paper, we propose GaPT, a novel toolkit that converts GPs to their state space form and performs regression in linear time. GaPT is designed to be highly compatible with several optimizers popular in robotics. We thoroughly validate the proposed approach for learning quadrotor dynamics on both single and multiple input GP settings. GaPT accurately captures the system behavior in multiple flight regimes and operating conditions, including those producing highly nonlinear effects such as aerodynamic forces and rotor interactions. Moreover, the results demonstrate the superior computational performance of GaPT compared to a classical GP inference approach on both single and multi-input settings especially when considering large number of data points, enabling real-time regression speed on embedded platforms used on SWaP-constrained aerial robots.

We demonstrate the difference The nature of anonymity and decentralization of blockchain between the estimated values of evaluation metrics and the systems are making changes in the finance industry due actual values through an engineered PU dataset from the to its immutability, transparency, and automation [1]. Such Ethereum transaction dataset proposed in [15] to show the decentralized systems, however, are in the current stage of a concerns of assuming unlabeled data to be normal. We conduct temporarily unregulated environment [2], [3] with a variety of experiments to show that applying various PU classifiers can abnormal usages and security concerns. The abnormal usages help in improving the classification performance on two realworld include both the illicit activities clearly defined by traditional datasets with limited positive labels. The PU classifiers fiance: phishing scams, Ponzi schemes, money laundering, estimate potential identifiable class prior or treat the unlabeled etc. [4], and also the activities with no clear definition of examples as negative samples with label noise and learn with lawfulness or being just defined such as mixing services, i.e., biased models. We also compare various graph representation the mixer nodes involve in funds to confuse the trace of the methods for extracting node embedding vectors as the input transfers from the original source, e.g., US Department of the to get diverse data distribution for the same data to obtain Treasury declared Tornado Cash as a sanctioned entity [5], [6].

This is a study on the potential widespread usage of alternative fuel vehicles, linking them with the socio-economic status of the respective consumers as well as the impact on the resulting air quality index. Research in this area aims to leverage machine learning techniques in order to promote appropriate policies for the proliferation of alternative fuel vehicles such as electric vehicles with due justice to different population groups. Pearson correlation coefficient is deployed in the modeling the relationships between socio-economic data, air quality index and data on alternative fuel vehicles. Linear regression is used to conduct predictive modeling on air quality index as per the adoption of alternative fuel vehicles, based on socio-economic factors. This work exemplifies artificial intelligence for social good.

Abstract: The Laser Interferometer Space Antenna (LISA) will provide us with a unique opportunity to observe the early inspiral phase of supermassive binary black holes (SMBBHs) in the mass range of 105 106M, that lasts for several years. It will also detect the merger and ringdown phases of these sources. Therefore, such sources are extremely useful for multiparameter tests of general relativity (GR), where parametrized deviations from GR at multiple post-Newtonian orders are simultaneously measured, thus allowing for a rigorous test of GR. However, the correlations of the deviation parameters with the intrinsic parameters of the system make multiparameter tests extremely challenging to perform. We demonstrate the use of principal component analysis (PCA) to obtain a new set of deviation parameters, which are best-measured orthogonal linear combinations of the original deviation parameters.