In this Paper we propose a simple yet effective set of local control rules to make a group of "herder agents" collect and contain in a desired region an ensemble of non-cooperative stochastic "target agents" in the plane. We investigate the robustness of the proposed strategies to variations of the number of target agents and the strength of the repulsive force they feel when in proximity of the herders. Extensive numerical simulations confirm the effectiveness of the approach and are complemented by a more realistic validation on commercially available robotic agents via ROS.

We introduce Dynabench, an open-source platform for dynamic dataset creation and model benchmarking. Dynabench runs in a web browser and supports human-and-model-in-the-loop dataset creation: annotators seek to create examples that a target model will misclassify, but that another person will not. In this paper, we argue that Dynabench addresses a critical need in our community: contemporary models quickly achieve outstanding performance on benchmark tasks but nonetheless fail on simple challenge examples and falter in real-world scenarios. With Dynabench, dataset creation, model development, and model assessment can directly inform each other, leading to more robust and informative benchmarks. We report on four initial NLP tasks, illustrating these concepts and highlighting the promise of the platform, and address potential objections to dynamic benchmarking as a new standard for the field.

Current limitations in boosted tree modelling prevent the effective scaling to datasets with a large feature number, particularly when investigating the magnitude and directionality of various features on classification. We present a novel methodology, Hollow-tree Super (HOTS), to resolve and visualize feature importance in boosted tree models involving a large number of features. Further, HOTS allows for investigation of the directionality and magnitude various features have on classification. Using the Iris dataset, we first compare HOTS to Gini Importance, Partial Dependence Plots, and Permutation Importance, and demonstrate how HOTS resolves the weaknesses present in these methods. We then show how HOTS can be utilized in high dimensional neuroscientific data, by taking 60 Schizophrenic subjects and applying the method to determine which brain regions were most important for classification of schizophrenia as determined by the PANSS. HOTS effectively replicated and supported the findings of Gini importance, Partial Dependence Plots and Permutation importance within the Iris dataset. When applied to the schizophrenic brain dataset, HOTS was able to resolve the top 10 most important features for classification, as well as their directionality for classification and magnitude compared to other features. Cross-validation supported that these same 10 features were consistently used in the decision-making process across multiple trees, and these features were localised primarily to the occipital and parietal cortices, commonly disturbed brain regions in those with Schizophrenia. It is imperative that a methodology is developed that is able to handle the demands of working with large datasets that contain a large number of features. HOTS represents a unique way to investigate both the directionality and magnitude of feature importance when working at scale with boosted-tree modelling.

We present our transducer model on Librispeech. We study variants to include an external language model (LM) with shallow fusion and subtract an estimated internal LM. This is justified by a Bayesian interpretation where the transducer model prior is given by the estimated internal LM. The subtraction of the internal LM gives us over 14% relative improvement over normal shallow fusion. Our transducer has a separate probability distribution for the non-blank labels which allows for easier combination with the external LM, and easier estimation of the internal LM. We additionally take care of including the end-of-sentence (EOS) probability of the external LM in the last blank probability which further improves the performance. All our code and setups are published.

Many decision making systems deployed in the real world are not static - a phenomenon known as model adaptation takes place over time. The need for transparency and interpretability of AI-based decision models is widely accepted and thus have been worked on extensively. Usually, explanation methods assume a static system that has to be explained. Explaining non-static systems is still an open research question, which poses the challenge how to explain model adaptations. In this contribution, we propose and (empirically) evaluate a framework for explaining model adaptations by contrastive explanations. We also propose a method for automatically finding regions in data space that are affected by a given model adaptation and thus should be explained.

Nearly two thousand government bodies, including police departments and public schools, have been using Clearview AI without oversight. Buzzfeed News reports that employees from 1,803 public bodies used the controversial facial-recognition platform without authorization from bosses. Reporters contacted a number of agency heads, many of which said they were unaware their employees were accessing the system. A database of searches, outlining which agencies were able to access the platform, and how many queries were made, was leaked to Buzzfeed by an anonymous source. It has published a version of the database online, enabling you to examine how many times each department has used the tool.

The university researchers built an agile contraption about the size of an average climbing lizard. The machine is nine inches long, weighs under a half-pound, and has legs and feet designed to mimic the way climbing lizards move. It is built primarily from 3-D-printed parts, with joints at the spine so it can slither and joints at the shoulders so its feet can move backward and forward. The feet have pushpins for claws, allowing them to grip into surfaces and release with ease.

In this work, we consider a binary classification problem and cast it into a binary hypothesis testing framework, where the observations can be perturbed by an adversary. To improve the adversarial robustness of a classifier, we include an abstaining option, where the classifier abstains from taking a decision when it has low confidence about the prediction. We propose metrics to quantify the nominal performance of a classifier with abstaining option and its robustness against adversarial perturbations. We show that there exist a tradeoff between the two metrics regardless of what method is used to choose the abstaining region. Our results imply that the robustness of a classifier with abstaining can only be improved at the expense of its nominal performance. Further, we provide necessary conditions to design the abstaining region for a 1-dimensional binary classification problem. We validate our theoretical results on the MNIST dataset, where we numerically show that the tradeoff between performance and robustness also exist for the general multi-class classification problems.

Confidence in the regulatory environment is crucial to enable responsible AI innovation and foster the social acceptance of these powerful new technologies. One notable source of uncertainty is, however, that the existing legal liability system is unable to assign responsibility where a potentially harmful conduct and/or the harm itself are unforeseeable, yet some instantiations of AI and/or the harms they may trigger are not foreseeable in the legal sense. The unpredictability of how courts would handle such cases makes the risks involved in the investment and use of AI difficult to calculate with confidence, creating an environment that is not conducive to innovation and may deprive society of some benefits AI could provide. To tackle this problem, we propose to draw insights from financial regulatory best practices and establish a system of AI guarantee schemes. We envisage the system to form part of the broader market-structuring regulatory frameworks, with the primary function to provide a readily available, clear, and transparent funding mechanism to compensate claims that are either extremely hard or impossible to realize via conventional litigation. We propose it to be at least partially industry-funded. Funding arrangements should depend on whether it would pursue other potential policy goals aimed more broadly at controlling the trajectory of AI innovation to increase economic and social welfare worldwide. Because of the global relevance of the issue, rather than focusing on any particular legal system, we trace relevant developments across multiple jurisdictions and engage in a high-level, comparative conceptual debate around the suitability of the foreseeability concept to limit legal liability. The paper also refrains from confronting the intricacies of the case law of specific jurisdictions for now and—recognizing the importance of this task—leaves this to further research in support of the legal system’s incremental adaptation to the novel challenges of present and future AI technologies. This article appears in the special track on AI and Society.

Manual labelling of training examples is common practice in supervised learning. When the labelling task is of non-trivial difficulty, the supplied labels may not be equal to the ground-truth labels, and label noise is introduced into the training dataset. If the manual annotation is carried out by multiple experts, the same training example can be given different class assignments by different experts, which is indicative of label noise. In the framework of model-based classification, a simple, but key observation is that when the manual labels are sampled using the posterior probabilities of class membership, the noisy labels are as valuable as the ground-truth labels in terms of statistical information. A relaxation of this process is a random effects model for imperfect labelling by a group that uses approximate posterior probabilities of class membership. The relative efficiency of logistic regression using the noisy labels compared to logistic regression using the ground-truth labels can then be derived. The main finding is that logistic regression can be robust to label noise when label noise and classification difficulty are positively correlated. In particular, when classification difficulty is the only source of label errors, multiple sets of noisy labels can supply more information for the estimation of a classification rule compared to the single set of ground-truth labels.