We investigate how the potential use of algorithms and demonstrative evidence may affect potential jurors' feelings of reliability, credibility, and understanding of expert witnesses and presented evidence. The use of statistical methods in forensic science is motivated by a lack of scientific validity and error rate issues present in many forensic analysis methods. We explore how this new method may be perceived in the courtroom - where individuals unfamiliar with advanced statistical methods are asked to evaluate its use in order to assess guilt. In the course of our initial study, we discovered issues in scale compression of responses and survey format. We visually compare participants' notes to the provided transcript by highlighting phrase frequency based on collocations.
相關內容
Quasiperiodic systems are important space-filling ordered structures, without decay and translational invariance. How to solve quasiperiodic systems accurately and efficiently is of great challenge. A useful approach, the projection method (PM) [J. Comput. Phys., 256: 428, 2014], has been proposed to compute quasiperiodic systems. Various studies have demonstrated that the PM is an accurate and efficient method to solve quasiperiodic systems. However, there is a lack of theoretical analysis of PM. In this paper, we present a rigorous convergence analysis of the PM by establishing a mathematical framework of quasiperiodic functions and their high-dimensional periodic functions. We also give a theoretical analysis of quasiperiodic spectral method (QSM) based on this framework. Results demonstrate that PM and QSM both have exponential decay, and the QSM (PM) is a generalization of the periodic Fourier spectral (pseudo-spectral) method. Then we analyze the computational complexity of PM and QSM in calculating quasiperiodic systems. The PM can use fast Fourier transform, while the QSM cannot. Moreover, we investigate the accuracy and efficiency of PM, QSM and periodic approximation method in solving the linear time-dependent quasiperiodic Schr\"{o}dinger equation.
The hyperparameters of recommender systems for top-n predictions are typically optimized to enhance the predictive performance of algorithms. Thereby, the optimization algorithm, e.g., grid search or random search, searches for the best hyperparameter configuration according to an optimization-target metric, like nDCG or Precision. In contrast, the optimized algorithm, internally optimizes a different loss function during training, like squared error or cross-entropy. To tackle this discrepancy, recent work focused on generating loss functions better suited for recommender systems. Yet, when evaluating an algorithm using a top-n metric during optimization, another discrepancy between the optimization-target metric and the training loss has so far been ignored. During optimization, the top-n items are selected for computing a top-n metric; ignoring that the top-n items are selected from the recommendations of a model trained with an entirely different loss function. Item recommendations suitable for optimization-target metrics could be outside the top-n recommended items; hiddenly impacting the optimization performance. Therefore, we were motivated to analyze whether the top-n items are optimal for optimization-target top-n metrics. In pursuit of an answer, we exhaustively evaluate the predictive performance of 250 selection strategies besides selecting the top-n. We extensively evaluate each selection strategy over twelve implicit feedback and eight explicit feedback data sets with eleven recommender systems algorithms. Our results show that there exist selection strategies other than top-n that increase predictive performance for various algorithms and recommendation domains. However, the performance of the top ~43% of selection strategies is not significantly different. We discuss the impact of our findings on optimization and re-ranking in recommender systems and feasible solutions.
We commonly encounter the problem of identifying an optimally weight adjusted version of the empirical distribution of observed data, adhering to predefined constraints on the weights. Such constraints often manifest as restrictions on the moments, tail behaviour, shapes, number of modes, etc., of the resulting weight adjusted empirical distribution. In this article, we substantially enhance the flexibility of such methodology by introducing a nonparametrically imbued distributional constraints on the weights, and developing a general framework leveraging the maximum entropy principle and tools from optimal transport. The key idea is to ensure that the maximum entropy weight adjusted empirical distribution of the observed data is close to a pre-specified probability distribution in terms of the optimal transport metric while allowing for subtle departures. The versatility of the framework is demonstrated in the context of three disparate applications where data re-weighting is warranted to satisfy side constraints on the optimization problem at the heart of the statistical task: namely, portfolio allocation, semi-parametric inference for complex surveys, and ensuring algorithmic fairness in machine learning algorithms.
From an information theoretic perspective, joint communication and sensing (JCAS) represents a natural generalization of communication network functionality. However, it requires the re-evaluation of network performance from a multi-objective perspective. We develop a novel mathematical framework for characterizing the sensing and communication coverage probability and ergodic rate in JCAS networks. We employ a formulation of sensing parameter estimation based on mutual information to extend the notions of coverage probability and ergodic rate to the radar setting. We define sensing coverage probability as the probability that the rate of information extracted about the parameters of interest associated with a typical radar target exceeds some threshold, and sensing ergodic rate as the spatial average of the aforementioned rate of information. Using this framework, we analyze the downlink sensing and communication coverage and rate of a mmWave JCAS network employing a shared waveform, directional beamforming, and monostatic sensing. Leveraging tools from stochastic geometry, we derive upper and lower bounds for these quantities. We also develop several general technical results including: i) a generic method for obtaining closed form upper and lower bounds on the Laplace Transform of a shot noise process, ii) a new analog of H{\"o}lder's Inequality to the setting of harmonic means, and iii) a relation between the Laplace and Mellin Transforms of a non-negative random variable. We use the derived bounds to numerically investigate the performance of JCAS networks under varying base station and blockage density. Among several insights, our numerical analysis indicates that network densification improves sensing SINR performance -- in contrast to communications.
Self-adaptation is a crucial feature of autonomous systems that must cope with uncertainties in, e.g., their environment and their internal state. Self-adaptive systems are often modelled as two-layered systems with a managed subsystem handling the domain concerns and a managing subsystem implementing the adaptation logic. We consider a case study of a self-adaptive robotic system; more concretely, an autonomous underwater vehicle (AUV) used for pipeline inspection. In this paper, we model and analyse it with the feature-aware probabilistic model checker ProFeat. The functionalities of the AUV are modelled in a feature model, capturing the AUV's variability. This allows us to model the managed subsystem of the AUV as a family of systems, where each family member corresponds to a valid feature configuration of the AUV. The managing subsystem of the AUV is modelled as a control layer capable of dynamically switching between such valid feature configurations, depending both on environmental and internal conditions. We use this model to analyse probabilistic reward and safety properties for the AUV.
How scientists navigate between the need to capitalize on their prior knowledge by specializing, and the urge to adapt to evolving research opportunities? Drawing from diverse perspectives on adaptation, in particular from institutional change and cultural evolution, this paper proposes an unsupervised Bayesian model of the evolution of scientists' research portfolios in response to transformations in their field. The model relies on scientific abstracts and authorship data to evaluate the influence of intellectual, social, and institutional resources on scientists' trajectories within a cohort of $2\,195$ high-energy physicists between 2000 and 2019. The reallocation of research efforts is shown to be shaped by learning costs, thus enhancing the utility of the scientific capital disseminated among scientists. Two dimensions of social capital, namely ``diversity'' and ``power'', have opposite effects on the magnitude of change in scientists' research interests: while ``diversity'' disrupts and expands research interests, ``power'' stabilizes physicists' research agendas -- as does institutional stability. Social capital plays a more crucial role in shifts between cognitively distant research areas. This contribution paves the way for further investigation of science and scientific communities as adaptative systems.
Wearable devices continuously collect sensor data and use it to infer an individual's behavior, such as sleep, physical activity, and emotions. Despite the significant interest and advancements in this field, modeling multimodal sensor data in real-world environments is still challenging due to low data quality and limited data annotations. In this work, we investigate representation learning for imputing missing wearable data and compare it with state-of-the-art statistical approaches. We investigate the performance of the transformer model on 10 physiological and behavioral signals with different masking ratios. Our results show that transformers outperform baselines for missing data imputation of signals that change more frequently, but not for monotonic signals. We further investigate the impact of imputation strategies and masking rations on downstream classification tasks. Our study provides insights for the design and development of masking-based self-supervised learning tasks and advocates the adoption of hybrid-based imputation strategies to address the challenge of missing data in wearable devices.
We present a large-scale empirical study of how choices of configuration parameters affect performance in knowledge distillation (KD). An example of such a KD parameter is the measure of distance between the predictions of the teacher and the student, common choices for which include the mean squared error (MSE) and the KL-divergence. Although scattered efforts have been made to understand the differences between such options, the KD literature still lacks a systematic study on their general effect on student performance. We take an empirical approach to this question in this paper, seeking to find out the extent to which such choices influence student performance across 13 datasets from 4 NLP tasks and 3 student sizes. We quantify the cost of making sub-optimal choices and identify a single configuration that performs well across the board.
Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents--computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extends a large language model to store a complete record of the agent's experiences using natural language, synthesize those memories over time into higher-level reflections, and retrieve them dynamically to plan behavior. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims, where end users can interact with a small town of twenty five agents using natural language. In an evaluation, these generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time. We demonstrate through ablation that the components of our agent architecture--observation, planning, and reflection--each contribute critically to the believability of agent behavior. By fusing large language models with computational, interactive agents, this work introduces architectural and interaction patterns for enabling believable simulations of human behavior.
This work considers the question of how convenient access to copious data impacts our ability to learn causal effects and relations. In what ways is learning causality in the era of big data different from -- or the same as -- the traditional one? To answer this question, this survey provides a comprehensive and structured review of both traditional and frontier methods in learning causality and relations along with the connections between causality and machine learning. This work points out on a case-by-case basis how big data facilitates, complicates, or motivates each approach.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191