The U.S. Food and Drug Administration recently partnered with Health Canada and the UK's Medicines and Healthcare products Regulatory Agency to issue guiding principles to align efforts and standards for artificial intelligence and machine learning medical device development in health care. "The FDA believes that artificial intelligence and machine learning technologies have the potential to transform health care by deriving new and important insights from the vast amount of data generated during the delivery of health care every day," said Jim McKinney, public affairs specialist at the FDA, in an email to The Well News. McKinney said the 10 guiding principles grew out of collaborative discussions with Health Canada and MHRA, and learning from several sectors that applied AI and ML technologies for years and have developed good practices that can be readily applied to the medical device industry. Evidence from published information, expert and other public perspectives and review experience was used to develop the guiding principles that will be used by the agency to lay the foundation for the development of Good Machine Learning Practice, which will unify international efforts for medical device development. Over the past decade the FDA has reviewed and authorized a growing number of devices legally marketed with machine learning and expects this trend to continue.

The relationship between artificial intelligence (AI) and defence is a longstanding one. The first "AI winter" of the 1970s, when interest in the subject evaporated and research work all but ceased, was due to Anglosphere government and defence bodies pulling the plug on funding. It's still widely believed that telephone conversations intercepted by Five Eyes intelligance agencies under the secret Echelon initiative are scanned in bulk for keywords of interest, allowing conversations of significance to be picked out from among millions of innocuous ones: but in fact, the problem of speech recognition, one of the main applications foreseen for AI, has yet to be completely solved even today. Back in the '70s a lack of tangible results led to an exhaustion of goodwill towards AI. It's common knowledge that military and intelligence interest can propel new technologies forward, and for a long while AI was without that safety net. But the story couldn't be more different today.

It's become increasingly comment nowadays for cybersecurity companies to market their products and solutions as AI-based. After all, if cybercriminals are getting smarter, then businesses will need smarter defenses to counter them. And which of us who are working down in the trenches of our IT profession can say they can keep up with the flood of new malware, vulnerabilities, and threats? The cyber landscape seems to be growing more dangerous each week, and there's no way you or I can learn all we need to know about these dangers and how to repel, mitigate or sidestep them. Enter artificial intelligence (AI) into the room.

Partially observable Markov decision processes (POMDPs) are models for sequential decision-making under uncertainty and incomplete information. Machine learning methods typically train recurrent neural networks (RNN) as effective representations of POMDP policies that can efficiently process sequential data. However, it is hard to verify whether the POMDP driven by such RNN-based policies satisfies safety constraints, for instance, given by temporal logic specifications. We propose a novel method that combines techniques from machine learning with the field of formal methods: training an RNN-based policy and then automatically extracting a so-called finite-state controller (FSC) from the RNN. Such FSCs offer a convenient way to verify temporal logic constraints. Implemented on a POMDP, they induce a Markov chain, and probabilistic verification methods can efficiently check whether this induced Markov chain satisfies a temporal logic specification. Using such methods, if the Markov chain does not satisfy the specification, a byproduct of verification is diagnostic information about the states in the POMDP that are critical for the specification. The method exploits this diagnostic information to either adjust the complexity of the extracted FSC or improve the policy by performing focused retraining of the RNN. The method synthesizes policies that satisfy temporal logic specifications for POMDPs with up to millions of states, which are three orders of magnitude larger than comparable approaches.

In December 2019, a novel virus called COVID-19 had caused an enormous number of causalities to date. The battle with the novel Coronavirus is baffling and horrifying after the Spanish Flu 2019. While the front-line doctors and medical researchers have made significant progress in controlling the spread of the highly contiguous virus, technology has also proved its significance in the battle. Moreover, Artificial Intelligence has been adopted in many medical applications to diagnose many diseases, even baffling experienced doctors. Therefore, this survey paper explores the methodologies proposed that can aid doctors and researchers in early and inexpensive methods of diagnosis of the disease. Most developing countries have difficulties carrying out tests using the conventional manner, but a significant way can be adopted with Machine and Deep Learning. On the other hand, the access to different types of medical images has motivated the researchers. As a result, a mammoth number of techniques are proposed. This paper first details the background knowledge of the conventional methods in the Artificial Intelligence domain. Following that, we gather the commonly used datasets and their use cases to date. In addition, we also show the percentage of researchers adopting Machine Learning over Deep Learning. Thus we provide a thorough analysis of this scenario. Lastly, in the research challenges, we elaborate on the problems faced in COVID-19 research, and we address the issues with our understanding to build a bright and healthy environment.

Monitoring news content automatically is an important problem. The news content, unlike traditional text, has a temporal component. However, few works have explored the combination of natural language processing and dynamic system models. One reason is that it is challenging to mathematically model the nuances of natural language. In this paper, we discuss how we built a novel dataset of news articles collected over time. Then, we present a method of converting news text collected over time to a sequence of directed multi-graphs, which represent semantic triples (Subject ! Predicate ! Object). We model the dynamics of specific topological changes from these graphs using discrete-time Hawkes processes. With our real-world data, we show that analyzing the structures of the graphs and the discrete-time Hawkes process model can yield insights on how the news events were covered and how to predict how it may be covered in the future.

Continuous deep learning architectures enable learning of flexible probabilistic models for predictive modeling as neural ordinary differential equations (ODEs), and for generative modeling as continuous normalizing flows. In this work, we design a framework to decipher the internal dynamics of these continuous depth models by pruning their network architectures. Our empirical results suggest that pruning improves generalization for neural ODEs in generative modeling. We empirically show that the improvement is because pruning helps avoid mode-collapse and flatten the loss surface. Moreover, pruning finds efficient neural ODE representations with up to 98% less parameters compared to the original network, without loss of accuracy. We hope our results will invigorate further research into the performance-size trade-offs of modern continuous-depth models.

Who is winning the race for jobs between robots and humans? Last year, two leading economists described a future in which humans come out ahead. But now they've declared a different winner: the robots. The industry most affected by automation is manufacturing. For every robot per thousand workers, up to six workers lost their jobs and wages fell by as much as three-fourths of a percent, according to a new paper by the economists, Daron Acemoglu of M.I.T. and Pascual Restrepo of Boston University.

The timeframe for NASA's return to the moon is in question, but when it does, it will have to decide what it wants its astronauts to cruise around the lunar surface in. Northrop Grumman announced on Tuesday that it is designing a Lunar Terrain Vehicle (LTV) to transport the agency's Artemis astronauts around the moon. It is teaming with several different companies, including AVL, tiremaker Michelin, Lunar Outpost and Intuitive Machines to design the rover. The announcement comes just hours after a government watchdog said NASA will miss its target for landing humans on the moon in late 2024 by'several years.' Northrop Grumman announced on Tuesday that it is designing a Lunar Terrain Vehicle (LTV) to transport the agency's Artemis astronauts around the moon A report from NASA's inspector general said cost overruns and the time needed to proper testing were the likely reasons NASA would miss the target date to return to the moon.

The Morrison Government is investing $10 million in innovative artificial intelligence (AI) technologies that will strengthen Defence's military capability and support highly skilled jobs in Australia's defence industry. The investment supports the Government's new Blueprint for Critical Technologies and Action Plan, released by the Prime Minister yesterday. It also contributes to the development of a sovereign critical technology capability in AI, one of the Government's nine listed critical technologies of national interest. Minister for Defence Industry and Science and Technology Melissa Price today announced 10 new Defence Innovation Hub contracts funded under the Government's two-year, $32 million COVID economic stimulus package. The package was established to support jobs growth in the defence industry while navigating the challenges posed by the pandemic.