Though inverse approach is computationally efficient in aerodynamic design as the desired target performance distribution is specified, it has some significant limitations that prevent full efficiency from being achieved. First, the iterative procedure should be repeated whenever the specified target distribution changes. Target distribution optimization can be performed to clarify the ambiguity in specifying this distribution, but several additional problems arise in this process such as loss of the representation capacity due to parameterization of the distribution, excessive constraints for a realistic distribution, inaccuracy of quantities of interest due to theoretical/empirical predictions, and the impossibility of explicitly imposing geometric constraints. To deal with these issues, a novel inverse design optimization framework with a two-step deep learning approach is proposed. A variational autoencoder and multi-layer perceptron are used to generate a realistic target distribution and predict the quantities of interest and shape parameters from the generated distribution, respectively. Then, target distribution optimization is performed as the inverse design optimization. The proposed framework applies active learning and transfer learning techniques to improve accuracy and efficiency. Finally, the framework is validated through aerodynamic shape optimizations of the airfoil of a wind turbine blade, where inverse design is actively being applied. The results of the optimizations show that this framework is sufficiently accurate, efficient, and flexible to be applied to other inverse design engineering applications.

Around 70% of 96 strategic goals under Vision 2030 are related to data and AI. - The growing investment toward smart cities in Saudi Arabia results in massively increasing adoption of AI solutions along with 5G and software, such as predictive analytics. In 2021, Saudi Arabian Crown Prince Mohammed bin Salman announced plans to build The Line, a 105-mile-long belt of hyper-connected communities in the kingdom's northeast that will feature no cars, no streets, and carbon emissions but will have smart infrastructure costing up to USD 200 billion.

China plans to launch a fleet of mile-long solar panels into space by 2035 and beam the energy back to Earth in a bid to meet its 2060 carbon neutral target. Reports suggest that once fully operational by 2050, the space-based solar array will send a similar amount of electricity into the grid as a nuclear power station. The idea for a space power station was first suggested by science-fiction writer Isaac Asimov in 1941 and has been explored by several countries including the UK and US. Above the Earth there are no clouds and no day or night that could obstruct the sun's ray – making a space solar station a constant zero carbon power source. However, the Chinese government appear to be ready to go from exploring the science and technology behind the idea, to putting a system into practice.

Eufy's SoloCam E40 eliminates a couple of pain points common to many home security cameras. Powered by a rechargeable battery, the E40 offers a wire-free installation that removes such logistical challenges as finding a convenient electrical outlet or installing entirely new electrical wiring that can make outdoor installations vexing. Secondly, it includes 8GB of onboard storage that stores about a month worth of video recordings, so you don't need to buy a cloud subscription to get the maximum security benefit from the camera. The E40 has a rectangular body similar to the EufyCam 2, enabling it to stand freely on any flat surface. It comes with a compact wall mount that screws into the back of the camera and can be affixed to a wall with the accompanying hardware.

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their critically central yet incomplete character. This report provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse, economic and environmental impact, legal and ethical considerations). Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization. Homogenization provides powerful leverage but demands caution, as the defects of the foundation model are inherited by all the adapted models downstream. Despite the impending widespread deployment of foundation models, we currently lack a clear understanding of how they work, when they fail, and what they are even capable of due to their emergent properties. To tackle these questions, we believe much of the critical research on foundation models will require deep interdisciplinary collaboration commensurate with their fundamentally sociotechnical nature.

Modelling the near-wall region of wall-bounded turbulent flows is a widespread practice to reduce the computational cost of large-eddy simulations (LESs) at high Reynolds number. As a first step towards a data-driven wall-model, a neural-network-based approach to predict the near-wall behaviour in a turbulent open channel flow is investigated. The fully-convolutional network (FCN) proposed by Guastoni et al. [preprint, arXiv:2006.12483] is trained to predict the two-dimensional velocity-fluctuation fields at $y^{+}_{\rm target}$, using the sampled fluctuations in wall-parallel planes located farther from the wall, at $y^{+}_{\rm input}$. The data for training and testing is obtained from a direct numerical simulation (DNS) at friction Reynolds numbers $Re_{\tau} = 180$ and $550$. The turbulent velocity-fluctuation fields are sampled at various wall-normal locations, i.e. $y^{+} = \{15, 30, 50, 80, 100, 120, 150\}$. At $Re_{\tau}=550$, the FCN can take advantage of the self-similarity in the logarithmic region of the flow and predict the velocity-fluctuation fields at $y^{+} = 50$ using the velocity-fluctuation fields at $y^{+} = 100$ as input with less than 20% error in prediction of streamwise-fluctuations intensity. These results are an encouraging starting point to develop a neural-network based approach for modelling turbulence at the wall in numerical simulations.

We study the problem of controlling a partially observed Markov decision process (POMDP) to either aid or hinder the estimation of its state trajectory by optimising the conditional entropy of the state trajectory given measurements and controls, a quantity we dub the smoother entropy. Our consideration of the smoother entropy contrasts with previous active state estimation and obfuscation approaches that instead resort to measures of marginal (or instantaneous) state uncertainty due to tractability concerns. By establishing novel expressions of the smoother entropy in terms of the usual POMDP belief state, we show that our active estimation and obfuscation problems can be reformulated as Markov decision processes (MDPs) that are fully observed in the belief state. Surprisingly, we identify belief-state MDP reformulations of both active estimation and obfuscation with concave cost and cost-to-go functions, which enables the use of standard POMDP techniques to construct tractable bounded-error (approximate) solutions. We show in simulations that optimisation of the smoother entropy leads to superior trajectory estimation and obfuscation compared to alternative approaches. Index Terms Partially observed Markov decision process (POMDP), entropy, estimation, directed information. The problem of controlling a stochastic dynamical system to either aid or hinder the estimation of its time-varying state arises across numerous applications in automatic control, signal processing, and robotics.

Nonlinear stochastic modeling is useful for describing complex engineering systems. Meanwhile, neuromorphic (brain-inspired) computing paradigms are developing to tackle tasks that are challenging and resource intensive on digital computers. An emerging scheme is reservoir computing which exploits nonlinear dynamical systems for temporal information processing. This paper introduces reservoir computers with output feedback as stationary and ergodic infinite-order nonlinear autoregressive models. We highlight the versatility of this approach by employing classical and quantum reservoir computers to model synthetic and real data sets, further exploring their potential for control applications.

Leaping around an obstacle course and pulling off backflips, this eerily human-like robot is only too happy to show off its parkour skills. Named Atlas, the humanoid was filmed by Boston Dynamics -- the firm behind the famous robotic dog Spot. The incredible footage shows the two-legged robot impressively maintaining its balance as it takes on a series of jumps, vaults and balance beams. They were set up by Boston Dynamics engineers to experiment with new behaviours for Atlas, as well as developing its whole-body athletics through a variety of rapidly changing, high-energy activities. Boston Dynamics engineers created the obstacle course to develop Atlas' whole-body athletics through a variety of rapidly changing, high-energy activities The humanoid, which was first unveiled to the public in July 2013, measures 1.5m (4.9ft) tall and weighs 75kg (11.8st).

Megan serves as Publishing Operations Manager at Emerj, and is currently attending The American University in Paris, where she is pursuing degrees in global communications and international business administration. Founded in 2003 as Tesla Motors, the electric vehicle and clean energy company based in California currently has a market cap of over $700 billion – making it more valuable than the top seven automakers combined. Today, Tesla is well-known for its electric vehicles but the company also produces products for sustainable energy generation and storage such as solar panels, solar roof tiles, and more to enable "homeowners, businesses, and utilities to manage renewable energy generation, storage, and consumption". Tesla claims that its mission is "to accelerate the world's transition to sustainable energy" and in 2020, the company sold over 500,000 units of its electric cars, exceeding 1 million vehicles produced. In the same year, Tesla also had the highest sales in the plug-in and battery electric passenger car segments.