Hyperdimensional computing (HDC) is a brain-inspired computing paradigm based on high-dimensional holistic representations of vectors. It recently gained attention for embedded smart sensing due to its inherent error-resiliency and suitability to highly parallel hardware implementations. In this work, we propose a programmable all-digital CMOS implementation of a fully autonomous HDC accelerator for always-on classification in energy-constrained sensor nodes. By using energy-efficient standard cell memory (SCM), the design is easily cross-technology mappable. It achieves extremely low power, 5 $\mu W$ in typical applications, and an energy-efficiency improvement over the state-of-the-art (SoA) digital architectures of up to 3$\times$ in post-layout simulations for always-on wearable tasks such as EMG gesture recognition. As part of the accelerator's architecture, we introduce novel hardware-friendly embodiments of common HDC-algorithmic primitives, which results in 3.3$\times$ technology scaled area reduction over the SoA, achieving the same accuracy levels in all examined targets. The proposed architecture also has a fully configurable datapath using microcode optimized for HDC stored on an integrated SCM based configuration memory, making the design "general-purpose" in terms of HDC algorithm flexibility. This flexibility allows usage of the accelerator across novel HDC tasks, for instance, a newly designed HDC applied to the task of ball bearing fault detection.

In this work we consider multitasking in the context of solving multiple optimization problems simultaneously by conducting a single search process. The principal goal when dealing with this scenario is to dynamically exploit the existing complementarities among the problems (tasks) being optimized, helping each other through the exchange of valuable knowledge. Additionally, the emerging paradigm of Evolutionary Multitasking tackles multitask optimization scenarios by using as inspiration concepts drawn from Evolutionary Computation. The main purpose of this survey is to collect, organize and critically examine the abundant literature published so far in Evolutionary Multitasking, with an emphasis on the methodological patterns followed when designing new algorithmic proposals in this area (namely, multifactorial optimization and multipopulation-based multitasking). We complement our critical analysis with an identification of challenges that remain open to date, along with promising research directions that can stimulate future efforts in this topic. Our discussions held throughout this manuscript are offered to the audience as a reference of the general trajectory followed by the community working in this field in recent times, as well as a self-contained entry point for newcomers and researchers interested to join this exciting research avenue.

In December, Heinrich-Böll-Stiftung hosted a virtual briefing featuring researchers from Climate Change AI (CCAI). They talked about the role machine learning can play in facilitating climate change mitigation and adaptation strategies, AI applications that increase emissions, and energy use in AI itself. On the topic of facilitating climate change mitigation and adaptation strategies, a number of examples were given where AI could help. These include: gathering information, forecasting, improving operational efficiencies, predictive maintenance, accelerating scientific experimentation, and approximating time-intensive simulations. The researchers then talked about AI applications that increase emissions.

Mixed-Integer Linear Programming (MILP) is concerned with the modelling and solving of problems from discrete optimisation. These problems can represent real-world scenarios, where discrete decisions can be appropriately captured and modelled by the integer variables. In real-world scenarios a MILP model is rarely solved only once. More frequently, the same model is used with varying data to describe different instances of the same problem which are solved on a regular basis. This holds true in particular for decision support systems, which can utilise MILP to provide real-time optimal decisions on a continual basis, see [4] and [40] for examples in nurse scheduling and vehicle routing. The MILPs that these decision support systems solve have identical structure due to both their underlying application and cyclical nature, and thus often have similar optimal solutions. Our aim is to exploit this repetitive structure, and create generative neural networks that generate binary decision encodings for subsets of important variables. These encodings can then be used in a primal heuristic by solving the induced sub-problem following variable fixations. Additionally, the then result of the primal heuristic can be used in a warm-start context to help improve solver performance in a globally optimal context.

Stochastic microstructure reconstruction involves digital generation of microstructures that match key statistics and characteristics of a (set of) target microstructure(s). This process enables computational analyses on ensembles of microstructures without having to perform exhaustive and costly experimental characterizations. Statistical functions-based and deep learning-based methods are among the stochastic microstructure reconstruction approaches applicable to a wide range of material systems. In this paper, we integrate statistical descriptors as well as feature maps from a pre-trained deep neural network into an overall loss function for an optimization based reconstruction procedure. This helps us to achieve significant computational efficiency in reconstructing microstructures that retain the critically important physical properties of the target microstructure. A numerical example for the microstructure reconstruction of bi-phase random porous ceramic material demonstrates the efficiency of the proposed methodology. We further perform a detailed finite element analysis (FEA) of the reconstructed microstructures to calculate effective elastic modulus, effective thermal conductivity and effective hydraulic conductivity, in order to analyse the algorithm's capacity to capture the variability of these material properties with respect to those of the target microstructure. This method provides an economic, efficient and easy-to-use approach for reconstructing random multiphase materials in 2D which has the potential to be extended to 3D structures.

Mobile robotics is a research area that has witnessed incredible advances for the last decades. Robot navigation is an essential task for mobile robots. Many methods are proposed for allowing robots to navigate within different environments. This thesis studies different deep learning-based approaches, highlighting the advantages and disadvantages of each scheme. In fact, these approaches are promising that some of them can navigate the robot in unknown and dynamic environments. In this thesis, one of the deep learning methods based on convolutional neural network (CNN) is realized by software implementations. There are different preparation studies to complete this thesis such as introduction to Linux, robot operating system (ROS), C++, python, and GAZEBO simulator. Within this work, we modified the drone network (namely, DroNet) approach to be used in an indoor environment by using a ground robot in different cases. Indeed, the DroNet approach suffers from the absence of goal-oriented motion. Therefore, this thesis mainly focuses on tackling this problem via mapping using simultaneous localization and mapping (SLAM) and path planning techniques using Dijkstra. Afterward, the combination between the DroNet ground robot-based, mapping, and path planning leads to a goal-oriented motion, following the shortest path while avoiding the dynamic obstacle. Finally, we propose a low-cost approach, for indoor applications such as restaurants, museums, etc, on the base of using a monocular camera instead of a laser scanner.

We investigate the use of spatial interpolation methods for reconstructing the horizontal near-surface wind field given a sparse set of measurements. In particular, random Fourier features is compared to a set of benchmark methods including Kriging and Inverse distance weighting. Random Fourier features is a linear model $\beta(\pmb x) = \sum_{k=1}^K \beta_k e^{i\omega_k \pmb x}$ approximating the velocity field, with frequencies $\omega_k$ randomly sampled and amplitudes $\beta_k$ trained to minimize a loss function. We include a physically motivated divergence penalty term $|\nabla \cdot \beta(\pmb x)|^2$, as well as a penalty on the Sobolev norm. We derive a bound on the generalization error and derive a sampling density that minimizes the bound. Following (arXiv:2007.10683 [math.NA]), we devise an adaptive Metropolis-Hastings algorithm for sampling the frequencies of the optimal distribution. In our experiments, our random Fourier features model outperforms the benchmark models.

Global optimization solves real-world problems numerically or analytically by minimizing their objective functions. Most of the analytical algorithms are greedy and computationally intractable. Metaheuristics are nature-inspired optimization algorithms. They numerically find a near-optimal solution for optimization problems in a reasonable amount of time. We propose a novel metaheuristic algorithm for global optimization. It is based on the shooting and jumping behaviors of the archerfish for hunting aerial insects. We name it the Archerfish Hunting Optimizer (AHO). We Perform two sorts of comparisons to validate the proposed algorithm's performance. First, AHO is compared to the 12 recent metaheuristic algorithms (the accepted algorithms for the 2020's competition on single objective bound-constrained numerical optimization) on ten test functions of the benchmark CEC 2020 for unconstrained optimization. Second, the performance of AHO and 3 recent metaheuristic algorithms, is evaluated using five engineering design problems taken from the benchmark CEC 2020 for non-convex constrained optimization. The experimental results are evaluated using the Wilcoxon signed-rank and the Friedman tests. The statistical indicators illustrate that the Archerfish Hunting Optimizer has an excellent ability to accomplish higher performance in competition with the well-established optimizers.

When NASA astronauts Mike Hopkins and Victor Glover went on a spacewalk on February 1st, they wrapped up a multi-year effort to replace the aging nickel hydrogen batteries on the ISS with new lithium-ion models. The International Space Station Program approved the development of lithium-ion batteries to replace the station's aging power storage system back in 2011. Battery production started in 2014, and the first lithium--ion replacements flew to the station aboard JAXA's Kounotori 6 resupply flight in December 2016. Now, four years after that flight and 14 spacewalks with 13 different astronauts later, the upgrade is finally complete. Ground controllers used the Canadarm2 robotic arm to position some of the batteries for installation.

His opinion lends credence to the assumption made in this article, namely that renewable energy, artificial intelligence (AI) and machine learning (ML) are not only intricately linked, but that'smart' renewable energy must be considered the most sustainable way forward for our energy needs. And it will increasingly continue to do so. Along with allied technologies such as ML, deep learning and advanced neural networks, AI has transformative potential for the global energy sector. An important caveat regarding the fossil fuel-renewable energy dichotomy will also be discussed at article's conclusion. ML is already entrenched in our everyday lives, from smart phone assistants like Apple's Siri or Samsung's Bixby, to voice and image recognition systems. More important even will be ML's ability to assist in tackling some of the world's most pressing physical and logistical problems, including that pertaining to the full potential of renewable energy.