In the context of designing and implementing ethical Artificial Intelligence (AI), varying perspectives exist regarding developing trustworthy AI for autonomous cars. This study sheds light on the differences in perspectives and provides recommendations to minimize such divergences. By exploring the diverse viewpoints, we identify key factors contributing to the differences and propose strategies to bridge the gaps. This study goes beyond the trolley problem to visualize the complex challenges of trustworthy and ethical AI. Three pillars of trustworthy AI have been defined: transparency, reliability, and safety. This research contributes to the field of trustworthy AI for autonomous cars, providing practical recommendations to enhance the development of AI systems that prioritize both technological advancement and ethical principles.
Over the past decades, cognitive neuroscientists and behavioral economists have recognized the value of describing the process of decision making in detail and modeling the emergence of decisions over time. For example, the time it takes to decide can reveal more about an agents true hidden preferences than only the decision itself. Similarly, data that track the ongoing decision process such as eye movements or neural recordings contain critical information that can be exploited, even if no decision is made. Here, we argue that artificial intelligence (AI) research would benefit from a stronger focus on insights about how decisions emerge over time and incorporate related process data to improve AI predictions in general and human-AI interactions in particular. First, we introduce a highly established computational framework that assumes decisions to emerge from the noisy accumulation of evidence, and we present related empirical work in psychology, neuroscience, and economics. Next, we discuss to what extent current approaches in multi-agent AI do or do not incorporate process data and models of decision making. Finally, we outline how a more principled inclusion of the evidence-accumulation framework into the training and use of AI can help to improve human-AI interactions in the future.
Context: Software model optimization is a process that automatically generates design alternatives, typically to enhance quantifiable non-functional properties of software systems, such as performance and reliability. Multi-objective evolutionary algorithms have shown to be effective in this context for assisting the designer in identifying trade-offs between the desired non-functional properties. Objective: In this work, we investigate the effects of imposing a time budget to limit the search for design alternatives, which inevitably affects the quality of the resulting alternatives. Method: The effects of time budgets are analyzed by investigating both the quality of the generated design alternatives and their structural features when varying the budget and the genetic algorithm (NSGA-II, PESA2, SPEA2). This is achieved by employing multi-objective quality indicators and a tree-based representation of the search space. Results: The study reveals that the time budget significantly affects the quality of Pareto fronts, especially for performance and reliability. NSGA-II is the fastest algorithm, while PESA2 generates the highest-quality solutions. The imposition of a time budget results in structurally distinct models compared to those obtained without a budget, indicating that the search process is influenced by both the budget and algorithm selection. Conclusions: In software model optimization, imposing a time budget can be effective in saving optimization time, but designers should carefully consider the trade-off between time and solution quality in the Pareto front, along with the structural characteristics of the generated models. By making informed choices about the specific genetic algorithm, designers can achieve different trade-offs.
This article investigates synthetic model-predictive control (MPC) problems to demonstrate that an increased precision of the internal prediction model (PM) automatially entails an improvement of the controller as a whole. In contrast to reinforcement learning (RL), MPC uses the PM to predict subsequent states of the controlled system (CS), instead of directly recommending suitable actions. To assess how the precision of the PM translates into the quality of the model-predictive controller, we compare a DNN-based PM to the optimal baseline PM for three well-known control problems of varying complexity. The baseline PM achieves perfect accuracy by accessing the simulation of the CS itself. Based on the obtained results, we argue that an improvement of the PM will always improve the controller as a whole, without considering the impact of other components such as action selection (which, in this article, relies on evolutionary optimization).
Benefiting from the development of deep learning, text-to-speech (TTS) techniques using clean speech have achieved significant performance improvements. The data collected from real scenes often contain noise and generally needs to be denoised by speech enhancement models. Noise-robust TTS models are often trained using the enhanced speech, which thus suffer from speech distortion and background noise that affect the quality of the synthesized speech. Meanwhile, it was shown that self-supervised pre-trained models exhibit excellent noise robustness on many speech tasks, implying that the learned representation has a better tolerance for noise perturbations. In this work, we therefore explore pre-trained models to improve the noise robustness of TTS models. Based on HIFI-GAN we first propose a representation-to-waveform vocoder, which aims to learn to map the representation of pre-trained models to the waveform. We then propose a text-to-representation Fastspeech2 model, which aims to learn to map text to pre-trained model representations. Experimental results on the LJSpeech and LibriTTS datasets show that our method outperforms those using speech enhancement methods in both subjective and objective metrics. Audio samples are available at: //zqs01.github.io/rep2wav/.
We aim to efficiently compute spreading speeds of reaction-diffusion-advection (RDA) fronts in divergence free random flows under the Kolmogorov-Petrovsky-Piskunov (KPP) nonlinearity. We study a stochastic interacting particle method (IPM) for the reduced principal eigenvalue (Lyapunov exponent) problem of an associated linear advection-diffusion operator with spatially random coefficients. The Fourier representation of the random advection field and the Feynman-Kac (FK) formula of the principal eigenvalue (Lyapunov exponent) form the foundation of our method implemented as a genetic evolution algorithm. The particles undergo advection-diffusion, and mutation/selection through a fitness function originated in the FK semigroup. We analyze convergence of the algorithm based on operator splitting, present numerical results on representative flows such as 2D cellular flow and 3D Arnold-Beltrami-Childress (ABC) flow under random perturbations. The 2D examples serve as a consistency check with semi-Lagrangian computation. The 3D results demonstrate that IPM, being mesh free and self-adaptive, is simple to implement and efficient for computing front spreading speeds in the advection-dominated regime for high-dimensional random flows on unbounded domains where no truncation is needed.
Variational autoencoders (VAEs) are popular likelihood-based generative models which can be efficiently trained by maximizing an Evidence Lower Bound (ELBO). There has been much progress in improving the expressiveness of the variational distribution to obtain tighter variational bounds and increased generative performance. Whilst previous work has leveraged Markov chain Monte Carlo (MCMC) methods for the construction of variational densities, gradient-based methods for adapting the proposal distributions for deep latent variable models have received less attention. This work suggests an entropy-based adaptation for a short-run Metropolis-adjusted Langevin (MALA) or Hamiltonian Monte Carlo (HMC) chain while optimising a tighter variational bound to the log-evidence. Experiments show that this approach yields higher held-out log-likelihoods as well as improved generative metrics. Our implicit variational density can adapt to complicated posterior geometries of latent hierarchical representations arising in hierarchical VAEs.
Many data science students and practitioners don't see the value in making time to learn and adopt good coding practices as long as the code "works". However, code standards are an important part of modern data science practice, and they play an essential role in the development of data acumen. Good coding practices lead to more reliable code and save more time than they cost, making them important even for beginners. We believe that principled coding is vital for quality data science practice. To effectively instill these practices within academic programs, instructors and programs need to begin establishing these practices early, to reinforce them often, and to hold themselves to a higher standard while guiding students. We describe key aspects of good coding practices for data science, illustrating with examples in R and in Python, though similar standards are applicable to other software environments. Practical coding guidelines are organized into a top ten list.
The estimands framework outlined in ICH E9 (R1) describes the components needed to precisely define the effects to be estimated in clinical trials, which includes how post-baseline "intercurrent" events (IEs) are to be handled. In late-stage clinical trials, it is common to handle intercurrent events like "treatment discontinuation" using the treatment policy strategy and target the treatment effect on all outcomes regardless of treatment discontinuation. For continuous repeated measures, this type of effect is often estimated using all observed data before and after discontinuation using either a mixed model for repeated measures (MMRM) or multiple imputation (MI) to handle any missing data. In basic form, both of these estimation methods ignore treatment discontinuation in the analysis and therefore may be biased if there are differences in patient outcomes after treatment discontinuation compared to patients still assigned to treatment, and missing data being more common for patients who have discontinued treatment. We therefore propose and evaluate a set of MI models that can accommodate differences between outcomes before and after treatment discontinuation. The models are evaluated in the context of planning a phase 3 trial for a respiratory disease. We show that analyses ignoring treatment discontinuation can introduce substantial bias and can sometimes underestimate variability. We also show that some of the MI models proposed can successfully correct the bias but inevitably lead to increases in variance. We conclude that some of the proposed MI models are preferable to the traditional analysis ignoring treatment discontinuation, but the precise choice of MI model will likely depend on the trial design, disease of interest and amount of observed and missing data following treatment discontinuation.
This paper aims to reconstruct the initial condition of a hyperbolic equation with an unknown damping coefficient. Our approach involves approximating the hyperbolic equation's solution by its truncated Fourier expansion in the time domain and using a polynomial-exponential basis. This truncation process facilitates the elimination of the time variable, consequently, yielding a system of quasi-linear elliptic equations. To globally solve the system without needing an accurate initial guess, we employ the Carleman contraction principle. We provide several numerical examples to illustrate the efficacy of our method. The method not only delivers precise solutions but also showcases remarkable computational efficiency.
Counterfactual prediction methods are required when a model will be deployed in a setting where treatment policies differ from the setting where the model was developed, or when the prediction question is explicitly counterfactual. However, estimating and evaluating counterfactual prediction models is challenging because one does not observe the full set of potential outcomes for all individuals. Here, we discuss how to tailor a model to a counterfactual estimand, how to assess the model's performance, and how to perform model and tuning parameter selection. We also provide identifiability results for measures of performance for a potentially misspecified counterfactual prediction model based on training and test data from the same (factual) source population. Last, we illustrate the methods using simulation and apply them to the task of developing a statin-na\"{i}ve risk prediction model for cardiovascular disease.