The recent AI boom has had all sorts of weird and wonderful side effects as amateur tinkerers find ways to repurpose research from universities and tech companies. But one of the more unexpected applications has been in the world of video game mods. Fans have discovered that machine learning is the perfect tool to improve the graphics of classic games. The technique being used is known as "AI upscaling." In essence, you feed an algorithm a low-resolution image, and, based on training data it's seen, it spits out a version that looks the same but has more pixels in it.

It is the near future. You wake in a house warmed by a heat pump that extracts energy from deep below the ground and delivers it to your home. You rise and make yourself a cup of tea – from water boiled on a hydrogen-burning kitchen stove. Then you head to work – in a robot-driven electric car directed by central control network to avoid traffic jams. At midday, you pause for lunch: a sandwich made of meat grown in a laboratory.

Sparse reward is one of the biggest challenges in reinforcement learning (RL). In this paper, we propose a novel method called Generative Exploration and Exploitation (GENE) to overcome sparse reward. GENE dynamically changes the start state of agent to the generated novel state to encourage the agent to explore the environment or to the generated rewarding state to boost the agent to exploit the received reward signal. GENE relies on no prior knowledge about the environment and can be combined with any RL algorithm, no matter on-policy or off-policy, single-agent or multi-agent. Empirically, we demonstrate that GENE significantly outperforms existing methods in four challenging tasks with only binary rewards indicating whether or not the task is completed, including Maze, Goal Ant, Pushing, and Cooperative Navigation. The ablation studies verify that GENE can adaptively tradeoff between exploration and exploitation as the learning progresses by automatically adjusting the proportion between generated novel states and rewarding states, which is the key for GENE to solving these challenging tasks effectively and efficiently.

The use of deep pretrained bidirectional transformers has led to remarkable progress in learning multi-sentence representations for downstream language understanding tasks (Devlin et al., 2018). For tasks that make pairwise comparisons, e.g. matching a given context with a corresponding response, two approaches have permeated the literature. A Cross-encoder performs full self-attention over the pair; a Bi-encoder performs self-attention for each sequence separately, and the final representation is a function of the pair. While Cross-encoders nearly always outperform Bi-encoders on various tasks, both in our work and others' (Urbanek et al., 2019), they are orders of magnitude slower, which hampers their ability to perform real-time inference. In this work, we develop a new architecture, the Poly-encoder, that is designed to approach the performance of the Cross-encoder while maintaining reasonable computation time. Additionally, we explore two pretraining schemes with different datasets to determine how these affect the performance on our chosen dialogue tasks: ConvAI2 and DSTC7 Track 1. We show that our models achieve state-of-the-art results on both tasks; that the Poly-encoder is a suitable replacement for Bi-encoders and Cross-encoders; and that even better results can be obtained by pretraining on a large dialogue dataset.

We study voting games on binary issues, where voters hold an objective over the outcome of the collective decision and are allowed, before the vote takes place, to negotiate their ballots with the other participants. We analyse the voters' rational behaviour in the resulting two-phase game when ballots are aggregated via non-manipulable rules and, more specifically, quota rules. We show under what conditions undesirable equilibria can be removed and desirable ones sustained as a consequence of the pre-vote phase.

In this article we will analyse how to compute the contribution of each input value to its aggregate output in some nonlinear models. Regression and classification applications, together with related algorithms for deep neural networks are presented. The proposed approach merges two methods currently present in the literature: integrated gradient and deep Taylor decomposition.

The $K$-means algorithm is extended to allow for partitioning of skewed groups. Our algorithm is called TiK-Means and contributes a $K$-means type algorithm that assigns observations to groups while estimating their skewness-transformation parameters. The resulting groups and transformation reveal general-structured clusters that can be explained by inverting the estimated transformation. Further, a modification of the jump statistic chooses the number of groups. Our algorithm is evaluated on simulated and real-life datasets and then applied to a long-standing astronomical dispute regarding the distinct kinds of gamma ray bursts.

In evidence-based medicine, relevance of medical literature is determined by predefined relevance conditions. The conditions are defined based on PICO elements, namely, Patient, Intervention, Comparator, and Outcome. Hence, PICO annotations in medical literature are essential for automatic relevant document filtering. However, defining boundaries of text spans for PICO elements is not straightforward. In this paper, we study the agreement of PICO annotations made by multiple human annotators, including both experts and non-experts. Agreements are estimated by a standard span agreement (i.e., matching both labels and boundaries of text spans), and two types of relaxed span agreement (i.e., matching labels without guaranteeing matching boundaries of spans). Based on the analysis, we report two observations: (i) Boundaries of PICO span annotations by individual human annotators are very diverse. (ii) Despite the disagreement in span boundaries, general areas of the span annotations are broadly agreed by annotators. Our results suggest that applying a standard agreement alone may undermine the agreement of PICO spans, and adopting both a standard and a relaxed agreements is more suitable for PICO span evaluation.

The (global) Lipschitz smoothness condition is crucial in establishing the convergence theory for most optimization methods. Unfortunately, most machine learning and signal processing problems are not Lipschitz smooth. This motivates us to generalize the concept of Lipschitz smoothness condition to the relative smoothness condition, which is satisfied by any finite-order polynomial objective function. Further, this work develops new Bregman-divergence based algorithms that are guaranteed to converge to a second-order stationary point for any relatively smooth problem. In addition, the proposed optimization methods cover both the proximal alternating minimization and the proximal alternating linearized minimization when we specialize the Bregman divergence to the Euclidian distance. Therefore, this work not only develops guaranteed optimization methods for non-Lipschitz smooth problems but also solves an open problem of showing the second-order convergence guarantees for these alternating minimization methods.

In this study, we propose the leveraging of interpretability for tasks beyond purely the purpose of explainability. In particular, this study puts forward a novel strategy for leveraging gradient-based interpretability in the realm of adversarial examples, where we use insights gained to aid adversarial learning. More specifically, we introduce the concept of spatially constrained one-pixel adversarial perturbations, where we guide the learning of such adversarial perturbations towards more susceptible areas identified via gradient-based interpretability. Experimental results using different benchmark datasets show that such a spatially constrained one-pixel adversarial perturbation strategy can noticeably improve the speed of convergence as well as produce successful attacks that were also visually difficult to perceive, thus illustrating an effective use of interpretability methods for tasks outside of the purpose of purely explainability.