For the last 20 years, the research on artificial intelligence has been very aggressive, which has resulted in great innovations. Big data, robotics, medical research, and autonomous vehicles are some of the applications that emerged from AI development. Government interest in AI has picked up in recent years as many government departments started to invest in AI in the form of pilot programs for various AI-based applications. AI adoption acts as a lever for transformational change in the way government services are conceived, designed, delivered, and consumed. It helps the government to provide integrated services to its citizens through the seamless flow of information across government departments.

China has prioritised Artificial Intelligence in its quest to become a powerful superpower under Xi Jinping. Beijing's interest in AI development and use stems from the fact that technology may be used for both civil and military objectives. As a result, while AI advances can benefit China's economy and healthcare, they can also help the People's Liberation Army (PLA) engage in "intelligent warfare", which PLA strategists define as "the implementation of artificial intelligence and its related technologies, such as cloud technology, data analytics, quantum information, and autonomous systems for military uses." AI and related technologies such as computer vision, human-machine teaming, neural connectivity, and autonomous systems also known as "intelligentized weapons", have been identified as critical to gaining an advantage in the next creation of warfare by China's military leaders and strategists. At the same time, they are concerned that other nations, particularly the United States, may surpass them in this area and develop the potential to overwhelm China's air defences and assault its command-and-control systems. As a result, China's central and provincial governments, the Chinese Communist Party (CCP), all PLA branches, and the country's state- and privately-owned industries are all working together.

In addition to the growing use of AI within surveillance systems across Africa, AI has also been integrated into weapon systems. Most prominently, lethal autonomous weapons systems use real-time sensor data coupled with AI and machine learning algorithms to "select and engage targets without further intervention by a human operator." Depending on how that definition is interpreted, the first use of a lethal autonomous weapon system in combat may have taken place on African soil in March 2020. That month, logistics units belonging to the armed forces of the Libyan warlord Khalifa Haftar came under attack by Turkish-made STM Kargu-2 drones as they fled Tripoli. According to a United Nations report, the Kargu-2 represented a lethal autonomous weapons system because it had been "programmed to attack targets without requiring data connectivity between the operator and munition."

According to The Future Health Index 2021, the AI/ML market in healthcare is among the most promising ones. About 40% of healthcare organization leaders in different countries consider the development of the above technologies a major driver for the future sustainability of global health. Let's talk about the trends and peculiarities of implementing AI/ML-based healthcare software solutions in the US and Europe. AI/ML is applied for diagnosing, treating, and predicting diseases, as well as for carefully planning the development of individual institutions and the system as a whole. According to research by MarketsandMarkets, ML is considered a leading technology in the healthcare market.

Scale AI's path to becoming a $7.3 billion company was paved in real data from images, text, voice and video. Now, it is using that foundation to get into the synthetic data game, one of the hotter and emerging categories in AI. They announced Wednesday an early access program to Scale Synthetic, a product that machine learning engineers can use to enhance their existing real-world data sets, according to the company. Scale hired two executives to build out this new division of its business. Scale hired Joel Kronander, who previously headed up machine learning at Nines and was a former computer vision engineer at Apple working on 3D mapping, as its new head of synthetic data.

Specialized accelerators have recently garnered attention as a method to reduce the power consumption of neural network inference. A promising category of accelerators utilizes nonvolatile memory arrays to both store weights and perform $\textit{in situ}$ analog computation inside the array. While prior work has explored the design space of analog accelerators to optimize performance and energy efficiency, there is seldom a rigorous evaluation of the accuracy of these accelerators. This work shows how architectural design decisions, particularly in mapping neural network parameters to analog memory cells, influence inference accuracy. When evaluated using ResNet50 on ImageNet, the resilience of the system to analog non-idealities - cell programming errors, analog-to-digital converter resolution, and array parasitic resistances - all improve when analog quantities in the hardware are made proportional to the weights in the network. Moreover, contrary to the assumptions of prior work, nearly equivalent resilience to cell imprecision can be achieved by fully storing weights as analog quantities, rather than spreading weight bits across multiple devices, often referred to as bit slicing. By exploiting proportionality, analog system designers have the freedom to match the precision of the hardware to the needs of the algorithm, rather than attempting to guarantee the same level of precision in the intermediate results as an equivalent digital accelerator. This ultimately results in an analog accelerator that is more accurate, more robust to analog errors, and more energy-efficient.

We benchmark the robustness of maximum likelihood based uncertainty estimation methods to outliers in training data for regression tasks. Outliers or noisy labels in training data results in degraded performances as well as incorrect estimation of uncertainty. We propose the use of a heavy-tailed distribution (Laplace distribution) to improve the robustness to outliers. This property is evaluated using standard regression benchmarks and on a high-dimensional regression task of monocular depth estimation, both containing outliers. In particular, heavy-tailed distribution based maximum likelihood provides better uncertainty estimates, better separation in uncertainty for out-of-distribution data, as well as better detection of adversarial attacks in the presence of outliers.

In selection processes such as hiring, promotion, and college admissions, implicit bias toward socially-salient attributes such as race, gender, or sexual orientation of candidates is known to produce persistent inequality and reduce aggregate utility for the decision maker. Interventions such as the Rooney Rule and its generalizations, which require the decision maker to select at least a specified number of individuals from each affected group, have been proposed to mitigate the adverse effects of implicit bias in selection. Recent works have established that such lower-bound constraints can be very effective in improving aggregate utility in the case when each individual belongs to at most one affected group. However, in several settings, individuals may belong to multiple affected groups and, consequently, face more extreme implicit bias due to this intersectionality. We consider independently drawn utilities and show that, in the intersectional case, the aforementioned non-intersectional constraints can only recover part of the total utility achievable in the absence of implicit bias. On the other hand, we show that if one includes appropriate lower-bound constraints on the intersections, almost all the utility achievable in the absence of implicit bias can be recovered. Thus, intersectional constraints can offer a significant advantage over a reductionist dimension-by-dimension non-intersectional approach to reducing inequality.

The "race" for dominance in AI is far from fair: Not only do a few developed economies possess certain material advantages right from the start, they also set the rules. They have an advantage in research and development, and possess a skilled workforce as well as wealth to invest in AI. We can also look at the state of inequity in AI in terms of governance: How "tech fluent" are policymakers in developing and underdeveloped countries? What barriers do they face in crafting regulations and industrial policy? Are they sufficiently represented and empowered at the international bodies that set rules and standards on AI? At the same time, there is an emerging challenge at the nexus of AI and climate change that could deepen this inequity.

Rohit Chopra has seized on nearly every public opportunity as director of the Consumer Financial Protection Bureau to admonish companies about the potential misuse of artificial intelligence in lending decisions. Chopra has said that algorithms can never "be free of bias" and may result in credit determinations that are unfair to consumers. He claims machine learning can be anti-competitive and could lead to "digital redlining" and "robo discrimination." The message for banks and fast-moving fintechs is loud and clear: Enforcement actions related to the use of AI are coming, as is potential guidance tied to what makes alternative data such as utility and rent payments risky when used in marketing, pricing and underwriting products, experts say. "The focus on artificial intelligence and machine learning is explicit," said Stephen Hayes, a partner at Relman Colfax PLLC and a former CFPB senior counsel.