Search for: All records

Abstract Ethical considerations are the fabric of society, and they foster cooperation, help, and sacrifice for the greater good. Advances in AI create a greater need to examine ethical considerations involving the development and implementation of such systems. Integrating ethics into artificial intelligence-based programs is crucial for preventing negative outcomes, such as privacy breaches and biased decision making. Human–AI teaming (HAIT) presents additional challenges, as the ethical principles and moral theories that provide justification for them are not yet computable by machines. To that effect, models of human judgments and decision making, such as the agent-deed-consequence (ADC) model, will be crucial to inform the ethical guidance functions in AI team mates and to clarify how and why humans (dis)trust machines. The current paper will examine the ADC model as it is applied to the context of HAIT, and the challenges associated with the use of human-centric ethical considerations when applied to an AI context. 

The deployment of vaccines across the US provides significant defense against serious illness and death from COVID-19. Over 70% of vaccine-eligible Americans are at least partially vaccinated, but there are pockets of the population that are under-vaccinated, such as in rural areas and some demographic groups (e.g. age, race, ethnicity). These unvaccinated pockets are extremely susceptible to the Delta variant, exacerbating the healthcare crisis and increasing the risk of new variants. In this paper, we describe a data-driven model that provides real-time support to Virginia public health officials by recommending mobile vaccination site placement in order to target under-vaccinated populations. Our strategy uses fine-grained mobility data, along with US Census and vaccination uptake data, to identify locations that are most likely to be visited by unvaccinated individuals. We further extend our model to choose locations that maximize vaccine uptake among hesitant groups. We show that the top recommended sites vary substantially across some demographics, demonstrating the value of developing customized recommendation models that integrate fine-grained, heterogeneous data sources. In addition, we used a statistically equivalent Synthetic Population to study the effect of combined demographics (eg, people of a particular race and age), which is not possible using US Census data alone. We validate our recommendations by analyzing the success rates of deployed vaccine sites, and show that sites placed closer to our recommended areas administered higher numbers of doses. Our model is the first of its kind to consider evolving mobility patterns in real-time for suggesting placement strategies customized for different targeted demographic groups. Our results will be presented at IAAI-22, but given the critical nature of the pandemic, we offer this extended version of that paper for more timely consideration of our approach and to cover additional findings. 

Understanding the nature of representation in neural networks is a goal shared by neuroscience and machine learning. It is therefore exciting that both fields converge not only on shared questions but also on similar approaches. A pressing question in these areas is understanding how the structure of the representation used by neural networks affects both their generalization, and robustness to perturbations. In this work, we investigate the latter by juxtaposing experimental results regarding the covariance spectrum of neural representations in the mouse V1 (Stringer et al) with artificial neural networks. We use adversarial robustness to probe Stringer et al's theory regarding the causal role of a 1/n covariance spectrum. We empirically investigate the benefits such a neural code confers in neural networks, and illuminate its role in multi-layer architectures. Our results show that imposing the experimentally observed structure on artificial neural networks makes them more robust to adversarial attacks. Moreover, our findings complement the existing theory relating wide neural networks to kernel methods, by showing the role of intermediate representations. 

Abstract We present a passive (unpowered) exoskeleton that assists the back during lifting. Our exoskeleton uses carbon fiber beams as the sole means to store energy and return it to the wearer. To motivate the design, we present general requirements for the design of a lifting exoskeleton, including calculating the required torque to support the torso for people of different weights and heights. We compare a number of methods of energy storage for exoskeletons in terms of mass, volume, hysteresis, and cycle life. We then discuss the design of our exoskeleton, and show how the torso assembly leads to balanced forces. We characterize the energy storage in the exoskeleton and the torque it provides during testing with human subjects. Ten participants performed freestyle, stoop, and squat lifts. Custom image processing software was used to extract the curvature of the carbon fiber beams in the exoskeleton to determine the stored energy. During freestyle lifting, it stores an average of 59.3 J and provides a peak torque of 71.7 Nm. 

There is a growing research interest in quantifying blood flow distribution for the entire cerebral circulation to sharpen diagnosis and improve treatment options for cerebrovascular disease of individual patients. We present a methodology to reconstruct subject‐specific cerebral blood flow patterns in accordance with physiological and fluid mechanical principles and optimally informed byin vivoneuroimage data of cerebrovascular anatomy and arterial blood flow rates. We propose an inverse problem to infer blood flow distribution across the visible portion of the arterial network that best matches subject‐specific anatomy and a given set of volumetric flow measurements. The optimization technique also mitigates the effect of uncertainties by reconciling incomplete flow data and by dissipating unavoidable acquisition errors associated with medical imaging data.