Nonnegative matrix factorization (NMF) has found many applications including topic modeling and document analysis. Hierarchical NMF (HNMF) variants are able to learn topics at various levels of granularity and illustrate their hierarchical relationship. Recently, nonnegative tensor factorization (NTF) methods have been applied in a similar fashion in order to handle data sets with complex, multi-modal structure. Hierarchical NTF (HNTF) methods have been proposed, however these methods do not naturally generalize their matrix-based counterparts. Here, we propose a new HNTF model which directly generalizes a HNMF model special case, and provide a supervised extension. We also provide a multiplicative updates training method for this model. Our experimental results show that this model more naturally illuminates the topic hierarchy than previous HNMF and HNTF methods.

Switching dynamical systems provide a powerful, interpretable modeling framework for inference in time-series data in, e.g., the natural sciences or engineering applications. Since many areas, such as biology or discrete-event systems, are naturally described in continuous time, we present a model based on an Markov jump process modulating a subordinated diffusion process. We provide the exact evolution equations for the prior and posterior marginal densities, the direct solutions of which are however computationally intractable. Therefore, we develop a new continuous-time variational inference algorithm, combining a Gaussian process approximation on the diffusion level with posterior inference for Markov jump processes. By minimizing the path-wise Kullback-Leibler divergence we obtain (i) Bayesian latent state estimates for arbitrary points on the real axis and (ii) point estimates of unknown system parameters, utilizing variational expectation maximization. We extensively evaluate our algorithm under the model assumption and for real-world examples.

This is a Women in AI Podcast transcript, for this interview we have Wendy Gonzalez, CEO at Sama, speaking with us about high-quality data training and what she's getting up to in her current role. We hope you enjoy the episode. Listen to the podcast here. So today I'm joined by Wendy Gonzalez on our Women in AI podcast episode, who is the Interim CEO of Sama, and I'm really excited to speak to her today. Hi, Wendy, how are you?

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.