Probabilistic circuits (PCs) are a family of generative models which allows for the computation of exact likelihoods and marginals of its probability distributions. PCs are both expressive and tractable, and serve as popular choices for discrete density estimation tasks. However, large PCs are susceptible to overfitting, and only a few regularization strategies (e.g., dropout, weight-decay) have been explored. We propose HyperSPNs: a new paradigm of generating the mixture weights of large PCs using a small-scale neural network. Our framework can be viewed as a soft weight-sharing strategy, which combines the greater expressiveness of large models with the better generalization and memory-footprint properties of small models. We show the merits of our regularization strategy on two state-of-the-art PC families introduced in recent literature -- RAT-SPNs and EiNETs -- and demonstrate generalization improvements in both models on a suite of density estimation benchmarks in both discrete and continuous domains.

The abductive natural language inference task ($\alpha$NLI) is proposed to infer the most plausible explanation between the cause and the event. In the $\alpha$NLI task, two observations are given, and the most plausible hypothesis is asked to pick out from the candidates. Existing methods model the relation between each candidate hypothesis separately and penalize the inference network uniformly. In this paper, we argue that it is unnecessary to distinguish the reasoning abilities among correct hypotheses; and similarly, all wrong hypotheses contribute the same when explaining the reasons of the observations. Therefore, we propose to group instead of ranking the hypotheses and design a structural loss called ``joint softmax focal loss'' in this paper. Based on the observation that the hypotheses are generally semantically related, we have designed a novel interactive language model aiming at exploiting the rich interaction among competing hypotheses. We name this new model for $\alpha$NLI: Interactive Model with Structural Loss (IMSL). The experimental results show that our IMSL has achieved the highest performance on the RoBERTa-large pretrained model, with ACC and AUC results increased by about 1\% and 5\% respectively.

This paper serves to introduce the reader to the field of multi-agent reinforcement learning (MARL) and its intersection with methods from the study of causality. We highlight key challenges in MARL and discuss these in the context of how causal methods may assist in tackling them. We promote moving toward a 'causality first' perspective on MARL. Specifically, we argue that causality can offer improved safety, interpretability, and robustness, while also providing strong theoretical guarantees for emergent behaviour. We discuss potential solutions for common challenges, and use this context to motivate future research directions.

When it comes to the implementation of Artificial Intelligence, a lot of people have started to acknowledge the impact and return it can have on their investments. But when companies actually decide to hop on the train of smart technology, one issue seems to always come up: data quality. Data is the essence of Artificial Intelligence. In itself, AI has existed for some time now. However, the reason it has gained such momentum in the last couple of years is specifically because of the humongous amount of data that is now being collected.

Tomb Raider recently celebrated its 25th anniversary, which means 25 years of articles about how Lara Croft transcended video games to become a global icon even your gran has heard of. As a female games critic, I am personally asked to explain her enduring popularity 25 times an hour, to the point where I have boiled my answer down to this: for many of us, she symbolises a moment in the history of gaming where we saw ourselves represented for the first time. Not as a princess trapped in a castle, but as an enigmatic, acrobatic embodiment of fierceness. Naturally, the adolescent boys of the 90s also regarded her with the same distanced respect, right? Anyway, here's what nobody says they remember fondly about Tomb Raider: the food.

As time goes by, it is more frequent that the use of artificial intelligence supports the activities we perform on a daily basis. Have you done a Google search recently, used Siri on your cell phone in the last few days, watched a movie on Netflix, played online games, listened to music on Spotify, or compared something on Amazon lately? If you've done any of these things, you've certainly come into contact with some artificial intelligence development. Over time, it is more frequent that artificial intelligence supports the activities we do daily. Every day, companies that have access to our data know us better and provide us with a better service.

NovaSignal's AI-driven automated cerebral doppler ultrasound system. Los Angeles based NovaSignal Inc. recently launched a second version of their artificial intelligence (AI)-guided robotic platform for assessing cerebral blood flow in order to guide real-time diagnosis. The platform uses ultrasound to autonomously capture blood flow data, which then gets sent to their HIPAA-compliant cloud system so that clinicians can access the exam data from anywhere on their personal devices. Founded in 2013, the company states they have raised over $25 million in federal research funding and hold 18 patents. They also have over 130 peer-reviewed citations to their work.

The research forecasts that the US and China will grow to account for over 60% of global smart hospital spending by 2026. It predicts that these countries' pre-existing smart hospital services, allied with the formulation of favourable reimbursement structures, will provide an ideal basis for further smart hospital roll-outs. However, it cautioned that the need for pre-existing digital infrastructure, such as electronic health records, will limit smart hospital roll-outs to developed regions. As a result, it anticipates that Latin America, Africa, and the Middle East will represent less than 5% of global smart hospital spending by 2026. Juniper Research's report outlined how a current lack of interoperability between devices and platforms has resulted in a high degree of fragmentation that will require regulatory intervention on a country-level basis. Research author Adam Wears explained: "Vendor lock-in and high investment requirements are the most prevalent issues for healthcare providers in adopting smart hospital services.

The growth of deep reinforcement learning (RL) has brought multiple exciting tools and methods to the field. This rapid expansion makes it important to understand the interplay between individual elements of the RL toolbox. We approach this task from an empirical perspective by conducting a study in the continuous control setting. We present multiple insights of fundamental nature, including: an average of multiple actors trained from the same data boosts performance; the existing methods are unstable across training runs, epochs of training, and evaluation runs; a commonly used additive action noise is not required for effective training; a strategy based on posterior sampling explores better than the approximated UCB combined with the weighted Bellman backup; the weighted Bellman backup alone cannot replace the clipped double Q-Learning; the critics' initialization plays the major role in ensemble-based actor-critic exploration. As a conclusion, we show how existing tools can be brought together in a novel way, giving rise to the Ensemble Deep Deterministic Policy Gradients (ED2) method, to yield state-of-the-art results on continuous control tasks from OpenAI Gym MuJoCo. From the practical side, ED2 is conceptually straightforward, easy to code, and does not require knowledge outside of the existing RL toolbox.

Commonsense knowledge (CSK) about concepts and their properties is useful for AI applications. Prior works like ConceptNet, COMET and others compiled large CSK collections, but are restricted in their expressiveness to subject-predicate-object (SPO) triples with simple concepts for S and strings for P and O. This paper presents a method, called ASCENT++, to automatically build a large-scale knowledge base (KB) of CSK assertions, with refined expressiveness and both better precision and recall than prior works. ASCENT++ goes beyond SPO triples by capturing composite concepts with subgroups and aspects, and by refining assertions with semantic facets. The latter is important to express the temporal and spatial validity of assertions and further qualifiers. ASCENT++ combines open information extraction with judicious cleaning and ranking by typicality and saliency scores. For high coverage, our method taps into the large-scale crawl C4 with broad web contents. The evaluation with human judgements shows the superior quality of the ASCENT++ KB, and an extrinsic evaluation for QA-support tasks underlines the benefits of ASCENT++. A web interface, data and code can be accessed at https://www.mpi-inf.mpg.de/ascentpp.