Single-task learning in artificial neural networks will be able to learn the model very well, and the benefits brought by transferring knowledge thus become limited. In this regard, when the number of tasks increases (e.g., semantic segmentation, panoptic segmentation, monocular depth estimation, and 3D point cloud), duplicate information may exist across tasks, and the improvement becomes less significant. Multi-task learning has emerged as a solution to knowledge-transfer issues and is an approach to scene understanding which involves multiple related tasks each with potentially limited training data. Multi-task learning improves generalization by leveraging the domain-specific information contained in the training data of related tasks. In urban management applications such as infrastructure development, traffic monitoring, smart 3D cities, and change detection, automated multi-task data analysis for scene understanding based on the semantic, instance, and panoptic annotation, as well as monocular depth estimation, is required to generate precise urban models. In this study, a common framework for the performance assessment of multi-task learning methods from fixed-wing UAV images for 2D/3D city modeling is presented.

The integration of learning and reasoning is one of the key challenges in artificial intelligence and machine learning today, and various communities have been addressing it. That is especially true for the field of neural-symbolic computation (NeSy) [10, 21], where the goal is to integrate symbolic reasoning and neural networks. NeSy already has a long tradition, and it has recently attracted a lot of attention from various communities (cf. the keynotes of Y. Bengio and H. Kautz on this topic at AAAI 2020, the AI Debate [9] between Y. Bengio and G. Marcus). Another domain that has a rich tradition in integrating learning and reasoning is that of statistical relational learning and artificial intelligence (StarAI) [39, 85]. But rather than focusing on integrating logic and neural networks, it is centred around the question of integrating logic with probabilistic reasoning, more specifically probabilistic graphical models. Despite the common interest in combining symbolic reasoning with a basic paradigm for learning, i.e., probabilistic graphical models or neural networks, it is surprising that there are not more interactions between these two fields.

Humans excel in solving complex reasoning tasks through a mental process of moving from one idea to a related one. Inspired by this, we propose Subgoal Search (kSubS) method. Its key component is a learned subgoal generator that produces a diversity of subgoals that are both achievable and closer to the solution. Using subgoals reduces the search space and induces a high-level search graph suitable for efficient planning. In this paper, we implement kSubS using a transformer-based subgoal module coupled with the classical best-first search framework. We show that a simple approach of generating $k$-th step ahead subgoals is surprisingly efficient on three challenging domains: two popular puzzle games, Sokoban and the Rubik's Cube, and an inequality proving benchmark INT. kSubS achieves strong results including state-of-the-art on INT within a modest computational budget.

As a boy, Eric Plosky '99, MCP '00, rode the New York subway with his grandmother to every city attraction on the map. "Whenever anyone asks me how I got into transportation, I always ask them, 'How did you get out of it?'" he says. "Every little kid seems to love trains and subways and buses and cars and planes, and for some reason they'grow out of it.' Now, as chief of transportation planning at the Volpe National Transportation Systems Center in Kendall Square, Plosky and his team put their imaginations to work reenvisioning what transportation can be. It's people, it's decision-making, it's history and culture," he says.

I recently fell in love with Explainable AI (XAI). XAI is a set of methods aimed at making increasingly complex machine learning (ML) models understandable by humans. XAI could help bridge the gap between AI and humans. That is very much needed as the gap is widening. Machine learning is proving incredibly successful in tackling problems from cancer diagnostics to fraud detection.

Africa has a knack for inventing and reinvigorating old technologies. To some degree, Africa has managed to sidestep this AI revolution and maintain its traditional way of life. That's because in Africa, artificial intelligence isn't really a thing yet - there are no driverless busses or pizza delivery robots that speak your local languages. Many discussions about the future of artificial intelligence in Africa, as well as why and how African countries have been slow to embrace this new technology trend have been had, so how do we move from these Conversations to implementation? The fact that Africa is so behind in artificial intelligence is a matter of concern - what are the effects of this new technology on African countries?

A U.S.-led coalition aircraft shot down an unmanned drone in Eastern Syria's Deir al-Zour province Saturday, months after the U.S. Central Command expressed concern over the use of weaponized drones to attack U.S. forces in the region. "Coalition aircraft successfully engaged and defeated a UAS through air to air engagement in the vicinity of Mission Support Site Green Village," Reuters quoted coalition spokesperson U.S. Army Colonel Wayne Marotto. While the coalition refused to reveal the type of aircraft used or other details citing security issues, a report by Aviation Week said a U.S. Air Force F-15E Strike Eagle used an AIM-9X Sidewinder missile to hit the UAS. The report added that Brig. Gen. Christopher Sage, commander of the 332nd Air Expeditionary Wing, was piloting the F-15E that fired the missile.

It's a question that Diana Akrong found herself asking last year. Diana is a UX researcher based in Accra, Ghana, and the founding member of Google's Accra UX team. Across the world, her manager Dr. Courtney Heldreth, was equally interested in answering this question. Courtney is a social psychologist and a staff UX researcher based in Seattle, and both women work as part of Google's People Artificial Intelligence Research (PAIR) group. "Looking back on history, we can see how the industrial revolution played a significant role in creating global inequality," she says.

Games have long been a fertile testing ground for the artificial intelligence community, and not just because of their accessibility to the popular imagination. Games also enable researchers to simulate different models of human intelligence, and to quantify performance. No surprise, then, that the 2016 victory of DeepMind's AlphaGo algorithm--developed by 2019 ACM Computing Prize recipient David Silver, who leads the company's Reinforcement Learning Research Group--over world Go champion Lee Sedol generated excitement both within and outside of the computing community. As it turned out, that victory was only the beginning; subsequent iterations of the algorithm have been able to learn without any human data or prior knowledge except the rules of the game and, eventually, without even knowing the rules. Here, Silver talks about how the work evolved and what it means for the future of general-purpose AI.

How do we deal with very large data sets of high resolution images, in particular in the field of radio astronomy? This question encompasses the scope of a joint PhD project between the University of Groningen (The Netherlands), the University of Stellenbosch (South Africa), and ASTRON, which is the Netherlands Institute for Radio Astronomy. Modern radio telescopes typically consist of 100 to a few hundred receiving elements, whose signals are pairwise correlated producing tens of thousands correlations for tens of thousands of frequency channels simultaneously. For a system like the Square Kilometre Array (SKA) this produces a data deluge of 1 TByte/s. This data may be affected by man-made radio frequency interference (RFI), instrumental failures and other effects that make the data unsuitable for scientific analysis.