China on Tuesday showed off its increasingly sophisticated air power including surveillance drones, with an eye on disputed territories from Taiwan to the South China Sea and its rivalry with the United States. The country's biggest airshow, in the southern coastal city of Zhuhai, comes as Beijing pushes to meet a 2035 deadline to retool its military for modern warfare. China still lags the United States in terms of tech and investment in its war machine, but experts say it is narrowing the gap. On Tuesday, the air force aerobatic team left colourful vapour trails as it manoeuvred in formation, while visitors inspected new jets, drones and attack helicopters on the tarmac. The CH-6, a prototype drone with a wingspan of 20.5 metres (67 feet), was among the domestic tech unveiled.

China on Tuesday showed off its increasingly sophisticated air power including surveillance drones and jets able to jam hostile electronic equipment, with an eye on disputed territories from Taiwan to the South China Sea and rivalry with the United States. The country's biggest airshow, in the southern coastal city of Zhuhai, comes as Beijing pushes to meet a 2035 deadline to retool its military for modern warfare. China still lags the United States in terms of tech and investment in its war machine, but experts say it is narrowing the gap. On Tuesday, a prototype of a new surveillance drone able to carry out attacks -- the CH-6 -- was among domestic tech unveiled in Zhuhai. China's WZ-7 high-altitude drone for border reconnaissance and maritime patrol has already entered service with the air force, according to state media Photo: AFP / Noel Celis With a wingspan of 20.5 metres (67 feet) and 15.8 metres long, the drone can carry missiles and is designed for surveillance and strike operations, according to open source intelligence agency Janes. Other debutants include the WZ-7 high-altitude drone for border reconnaissance and maritime patrol, as well as the J-16D fighter jet which can jam electronic equipment.

Artificial Intelligence (AI) for social good is a field of work which, broadly speaking, uses AI to make the world a better place. I had a chance to interview two leaders in the field, Dr. Bryan Wilder, who recently received his Ph.D. from Harvard (and will be joining the faculty at Carnegie Mellon next fall) and current Harvard Ph.D. student, Lily Xu. Both Bryan and Lily have been advised by Dr. Tambe, Gordon McKay Professor of Computer Science and Director of the Center for Research in Computation and Society (CRCS) at Harvard University and Director of AI for Social Good at Google Research India. While Bryan and Lily are both working at the intersection of AI and social good, they arrived at this junction via different paths. Bryan was studying computer science and looking for a field to apply his knowledge; his search led him to public health.

The successful training of neural networks typically involves careful and time consuming hyperparameter tuning. Population Based Training (PBT) has recently been proposed to automate this process. PBT trains a population of neural networks concurrently, frequently mutating their hyperparameters throughout their training. However, the decision mechanisms of PBT are greedy and favour short-term improvements which can, in some cases, lead to poor long-term performance. This paper presents Faster Improvement Rate PBT (FIRE PBT) which addresses this problem. Our method is guided by an assumption: given two neural networks with similar performance and training with similar hyperparameters, the network showing the faster rate of improvement will lead to a better final performance. Using this, we derive a novel fitness metric and use it to make some of the population members focus on long-term performance. Our experiments show that FIRE PBT is able to outperform PBT on the ImageNet benchmark and match the performance of networks that were trained with a hand-tuned learning rate schedule. We apply FIRE PBT to reinforcement learning tasks and show that it leads to faster learning and higher final performance than both PBT and random hyperparameter search.

Left-wing activist Michael Moore claimed Sunday that U.S. defense policy and spending should be refocused from military involvement in other countries to instead fight climate change, White supremacy and the coronavirus pandemic. Appearing on MSNBC, Moore suggested U.S. armed forces weren't "the good guys" because of their military involvement in countries like Syria and Somalia, and instead claimed he wanted to be known for doing "the good things," like building wells in poor villages rather than provide funding to Israel's Iron Dome defense system. "As we speak tonight the U.S. still has 2,500 troops in Iraq. Last week the U.S. military admitted that a drone strike in Kabul that killed ten innocent civilians was an American drone strike. Seven of them were kids. We talk about ending the war but we're still going to carry on with drones, we're still going to carry on with these, quote, over-the-horizon operations. You know, we are still at war," host Mehdi Hasan said after playing a clip of President Joe Biden touting the U.S. not being at war for the first time in 20 years.

Over the past few years, the Kingdom of Bahrain has made great and qualitative leaps in various economic, educational and technological fields, led by its leadership, regionally and globally, in the field of artificial intelligence and information technology. A field that is considered today one of the most important activities around the world, and attracts investments by major international companies, It is witnessing a state of competition, both at the governmental and private levels. The Kingdom of Bahrain would not have enjoyed this distinguished position in this vital field, except with the support and popularization of this vital sector by state officials, in addition the ability of Bahraini youth whom excel and a have a deep desire for creativity and innovation. His Highness Sheikh Khalid bin Hamad Al Khalifa, First Vice-President of the Supreme Council for Youth and Sports, is considered the first and true supporter in the field of technology for many students. In addition to His Highness's support for the category of people with disabilities through the "Science in Humanity" conference, as well as the "Techno for Disability" conference, where His Highness strives to enhance the capabilities of students of all groups and support them.

Dr Thaler's international crusade for recognition of machine inventorship (which I reported on last year) is nearing the end of the line in the UK. Last week, in Thaler v Comptroller General of Patents Trade Marks And Designs [2021] EWCA Civ 1374, the Court of Appeal upheld the rejection of his DABUS patent applications. In 2018, Dr Thaler, the owner of DABUS (an artificial intelligence ("AI") creativity machine) submitted two patent applications to the UKIPO naming himself as the owner and DABUS as the inventor. The UKIPO rejected his applications on the basis that, for the purposes of the Patents Act 1977 ("PA 1997"), the inventor must be a "person" (with legal personality, such as a human or a corporate entity), and considering how ownership is derived from inventorship, Dr Thaler could not be the owner in the absence of a valid inventor. In 2020, in the Court of First Instance, Marcus Smith J upheld the UKIPO's decision, concluding that section 7 PA 1997, which sets out the classes of persons to whom patents can be granted, could not be interpreted to cover non-legal persons such as machines. On that basis, he found that the UKIPO was entitled to withdraw Dr Thaler's application under section 13 PA 1997.

IonQ, Inc, the leader in quantum computing, announced the release of a new paper in collaboration with Fidelity Center for Applied Technology (FCAT) that demonstrates how its quantum computers can outperform classical computers to generate high-quality data for use in testing financial models. Financial institutions commonly use models for asset allocation, electronic trading, and pricing, and require testing data to validate the accuracy of these models. The new technique, demonstrated by FCAT on IonQ's latest quantum computers, has the potential to be the first class of quantum machine learning models to be deployed for broad commercial use. "At FCAT, we track new and emerging technologies and trends to help Fidelity meet the changing needs of our customers and ass These classical approaches are often limited because real-world dependencies between variables–for example, in a portfolio of stocks–are too complex for them to model. IonQ and FCAT demonstrated that data generated with quantum machine learning algorithms is more representative of these real-world dependencies and is therefore better at accounting for edge cases like black swan events. The technique invented by IonQ and FCAT leverages copulas, a method often used in statistical models to describe relationships between large numbers of variables. For instance, large financial institutions use copulas to understand relationships between stock prices (if the price of X is within a particular range, then the price of Y tends to go up). By using quantum computers to implement copulas, IonQ and FCAT demonstrated the ability to construct complex models beyond the capability of classical computers. "This research, performed on IonQ hardware, shows quite clearly that leveraging quantum computing can lead to superior financial modeling results.

Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems. Existing dynamic embedding methods on TIG discretely update node embeddings merely when an interaction occurs. They fail to capture the continuous dynamic evolution of embedding trajectories of nodes. In this paper, we propose a two-module framework named ConTIG, a continuous representation method that captures the continuous dynamic evolution of node embedding trajectories. With two essential modules, our model exploit three-fold factors in dynamic networks which include latest interaction, neighbor features and inherent characteristics. In the first update module, we employ a continuous inference block to learn the nodes' state trajectories by learning from time-adjacent interaction patterns between node pairs using ordinary differential equations. In the second transform module, we introduce a self-attention mechanism to predict future node embeddings by aggregating historical temporal interaction information. Experiments results demonstrate the superiority of ConTIG on temporal link prediction, temporal node recommendation and dynamic node classification tasks compared with a range of state-of-the-art baselines, especially for long-interval interactions prediction.

This paper provides an analysis of character-level machine translation models used in pivot-based translation when applied to sparse and noisy datasets, such as crowdsourced movie subtitles. In our experiments, we find that such character-level models cut the number of untranslated words by over 40% and are especially competitive (improvements of 2-3 BLEU points) in the case of limited training data. We explore the impact of character alignment, phrase table filtering, bitext size and the choice of pivot language on translation quality. We further compare cascaded translation models to the use of synthetic training data via multiple pivots, and we find that the latter works significantly better. Finally, we demonstrate that neither word-nor character-BLEU correlate perfectly with human judgments, due to BLEU's sensitivity to length.