Quantum physicist Mario Krenn remembers sitting in a café in Vienna in early 2016, poring over computer printouts, trying to make sense of what MELVIN had found. MELVIN was a machine-learning algorithm Krenn had built, a kind of artificial intelligence. Its job was to mix and match the building blocks of standard quantum experiments and find solutions to new problems. And it did find many interesting ones. But there was one that made no sense.

I can't tell you how excited I am to have you here with me, and I hope between us we can build not just a newsletter, but a news community. Sometimes there's a story that just sums up all the hopes and fears of its entire field. GitHub is a platform that lets developers collaborate on coding with colleagues, friends and strangers around the world, and host the results. Owned by Microsoft since 2018, the site is the largest host of source code in the world, and a crucial part of many companies' digital infrastructure. Late last month, GitHub launched a new AI tool, called Copilot.

Washington – Japan, the United States, Australia and India on Tuesday agreed on the need for democratic countries to strengthen their cooperation in developing advanced technologies, apparently to counter China's rise in the field. Ministers and other representatives from the "Quad" nations reached the agreement at an international meeting hosted by the National Security Commission on Artificial Intelligence (NSCAI), an independent commission of the U.S. Congress that makes recommendations to the U.S. president and Congress. The participants worked to deepen the ties in the Quad framework in the run-up to a summit the four nations' leaders aim to hold in autumn this year. "Today, emerging technologies such as the internet of things, 5G, artificial intelligence, quantum technology not only produce economic benefits but have the potential to affect civil liberties, human rights and even national security," science and technology minister Shinji Inoue said as he attended the event in Washington virtually. "It is very important for the Quad countries … which share common values, to cooperate in emerging technologies so that sustainable, inclusive, resilient economic growth can be promoted in the Indo-Pacific region," he said.

Most machine learning algorithms are configured by one or several hyperparameters that must be carefully chosen and often considerably impact performance. To avoid a time consuming and unreproducible manual trial-and-error process to find well-performing hyperparameter configurations, various automatic hyperparameter optimization (HPO) methods, e.g., based on resampling error estimation for supervised machine learning, can be employed. After introducing HPO from a general perspective, this paper reviews important HPO methods such as grid or random search, evolutionary algorithms, Bayesian optimization, Hyperband and racing. It gives practical recommendations regarding important choices to be made when conducting HPO, including the HPO algorithms themselves, performance evaluation, how to combine HPO with ML pipelines, runtime improvements, and parallelization.

Forgetting - or variable elimination - is an operation that allows the removal, from a knowledge base, of middle variables no longer deemed relevant. In recent years, many different approaches for forgetting in Answer Set Programming have been proposed, in the form of specific operators, or classes of such operators, commonly following different principles and obeying different properties. Each such approach was developed to somehow address some particular view on forgetting, aimed at obeying a specific set of properties deemed desirable in such view, but a comprehensive and uniform overview of all the existing operators and properties is missing. In this paper, we thoroughly examine existing properties and (classes of) operators for forgetting in Answer Set Programming, drawing a complete picture of the landscape of these classes of forgetting operators, which includes many novel results on relations between properties and operators, including considerations on concrete operators to compute results of forgetting and computational complexity. Our goal is to provide guidance to help users in choosing the operator most adequate for their application requirements.

Bus timetable optimization is a key issue to reduce operational cost of bus companies and improve the service quality. Existing methods use exact or heuristic algorithms to optimize the timetable in an offline manner. In practice, the passenger flow may change significantly over time. Timetables determined in offline cannot adjust the departure interval to satisfy the changed passenger flow. Aiming at improving the online performance of bus timetable, we propose a Deep Reinforcement Learning based bus Timetable dynamic Optimization method (DRL-TO). In this method, the timetable optimization is considered as a sequential decision problem. A Deep Q-Network (DQN) is employed as the decision model to determine whether to dispatch a bus service during each minute of the service period. Therefore, the departure intervals of bus services are determined in real time in accordance with passenger demand. We identify several new and useful state features for the DQN, including the load factor, carrying capacity utilization rate, and the number of stranding passengers. Taking into account both the interests of the bus company and passengers, a reward function is designed, which includes the indicators of full load rate, empty load rate, passengers' waiting time, and the number of stranding passengers. Building on an existing method for calculating the carrying capacity, we develop a new technique to enhance the matching degree at each bus station. Experiments demonstrate that compared with the timetable generated by the state-of-the-art bus timetable optimization approach based on a memetic algorithm (BTOA-MA), Genetic Algorithm (GA) and the manual method, DRL-TO can dynamically determine the departure intervals based on the real-time passenger flow, saving 8$\%$ of vehicles and reducing 17$\%$ of passengers' waiting time on average.

An impact of climate change is the increase in frequency and intensity of extreme precipitation events. However, confidently predicting the likelihood of extreme precipitation at seasonal scales remains an outstanding challenge. Here, we present an approach to forecasting the quantiles of the maximum daily precipitation in each week up to six months ahead using the temporal fusion transformer (TFT) model. Through experiments in two regions, we compare TFT predictions with those of two baselines: climatology and a calibrated ECMWF SEAS5 ensemble forecast (S5). Our results show that, in terms of quantile risk at six month lead time, the TFT predictions significantly outperform those from S5 and show an overall small improvement compared to climatology. The TFT also responds positively to departures from normal that climatology cannot.

We investigate the effect of using human demonstration data in the replay buffer for Deep Reinforcement Learning. We use a policy gradient method with a modified experience replay buffer where a human demonstration experience is sampled with a given probability. We analyze different ratios of using demonstration data in a task where an agent attempts to reach a goal while avoiding obstacles. Our results suggest that while the agents trained by pure self-exploration and pure demonstration had similar success rates, the pure demonstration model converged faster to solutions with less number of steps.

One of the most pressing problems in the automated analysis of historical documents is the availability of annotated training data. In this paper, we propose a novel method for the synthesis of training data for semantic segmentation of document images. We utilize clusters found in intermediate features of a StyleGAN generator for the synthesis of RGB and label images at the same time. Our model can be applied to any dataset of scanned documents without the need for manual annotation of individual images, as each model is custom-fit to the dataset. In our experiments, we show that models trained on our synthetic data can reach competitive performance on open benchmark datasets for line segmentation.

We describe several additions to the ENIGMA system that guides clause selection in the E automated theorem prover. First, we significantly speed up its neural guidance by adding server-based GPU evaluation. The second addition is motivated by fast weight-based rejection filters that are currently used in systems like E and Prover9. Such systems can be made more intelligent by instead training fast versions of ENIGMA that implement more intelligent pre-filtering. This results in combinations of trainable fast and slow thinking that improves over both the fast-only and slow-only methods. The third addition is based on "judging the children by their parents", i.e., possibly rejecting an inference before it produces a clause. This is motivated by standard evolutionary mechanisms, where there is always a cost to producing all possible offsprings in the current population. This saves time by not evaluating all clauses by more expensive methods and provides a complementary view of the generated clauses. The methods are evaluated on a large benchmark coming from the Mizar Mathematical Library, showing good improvements over the state of the art.