Canadian supercluster based in Montreal, SCALE AI acts as an investment and innovation hub to accelerate the adoption and rapid integration of AI in Canada. This Monday, August 22, it unveiled twelve new projects aimed at optimizing production and transportation through AI. With the goal of addressing critical challenges currently facing supply chains, including the impact of the pandemic, labor shortages, and environmental requirements, it will provide $50 million in unprecedented financial support. Funded by the federal and Quebec governments, SCALE AI brings together the retail, manufacturing, transportation, infrastructure and information and communications technology (ICT) sectors to build smart supply chains. The supercluster has nearly 500 industrial partners, research institutions and other AI players with whom it develops programs to support investment projects by companies implementing concrete AI applications.

Driven by the goal of eradicating language barriers on a global scale, machine translation has solidified itself as a key focus of artificial intelligence research today. However, such efforts have coalesced around a small subset of languages, leaving behind the vast majority of mostly low-resource languages. What does it take to break the 200 language barrier while ensuring safe, high quality results, all while keeping ethical considerations in mind? In No Language Left Behind, we took on this challenge by first contextualizing the need for low-resource language translation support through exploratory interviews with native speakers. Then, we created datasets and models aimed at narrowing the performance gap between low and high-resource languages. More specifically, we developed a conditional compute model based on Sparsely Gated Mixture of Experts that is trained on data obtained with novel and effective data mining techniques tailored for low-resource languages. We propose multiple architectural and training improvements to counteract overfitting while training on thousands of tasks. Critically, we evaluated the performance of over 40,000 different translation directions using a human-translated benchmark, Flores-200, and combined human evaluation with a novel toxicity benchmark covering all languages in Flores-200 to assess translation safety. Our model achieves an improvement of 44% BLEU relative to the previous state-of-the-art, laying important groundwork towards realizing a universal translation system.

Drop-on-demand (DOD) inkjet printing has been considered as one of promising technologies for the fabrication of advanced functional materials. For a DOD printer, high-precision dispensing techniques for achieving satellite-free smaller droplets, have long been desired for patterning thin-film structures. The present study considers the inlet velocity of a liquid chamber located upstream of a dispensing nozzle as a control variable and aims to optimize its waveform using a sample-efficient Bayesian optimization algorithm. Firstly, the droplet dispensing dynamics are numerically reproduced by using an open-source OpenFOAM solver, interFoam, and the results are passed on to another code based on pyFoam. Then, the parameters characterizing the actuation waveform driving a DOD printer are determined by the Bayesian optimization (BO) algorithm so as to maximize a prescribed multi-objective function expressed as the sum of two factors, i.e., the size of a primary droplet and the presence of satellite droplets. The results show that the present BO algorithm can successfully find high-precision dispensing waveforms within 150 simulations. Specifically, satellite droplets can be effectively eliminated and the droplet diameter can be significantly reduced to 24.9% of the nozzle diameter by applying the optimal waveform.

In this paper, we hypothesize that internal function sharing is one of the reasons to weaken o.o.d. or systematic generalization in deep learning for classification tasks. Under equivalent prediction, a model partitions an input space into multiple parts separated by boundaries. The function sharing prefers to reuse boundaries, leading to fewer parts for new outputs, which conflicts with systematic generalization. We show such phenomena in standard deep learning models, such as fully connected, convolutional, residual networks, LSTMs, and (Vision) Transformers. We hope this study provides novel insights into systematic generalization and forms a basis for new research directions. Source codes are available at https://github.com/

In present study, the effects of flight mach number, flight altitude, fuel types, and intake air temperature on thrust specific fuel consumption (TSFC), thrust, intake air mass flow rate, thermal and propulsive efficiency, as well as the exergetic efficiency and the exergy destruction rate in F135 PW100 engine are investigated. Based on the results obtained in the first phase, to model the thermodynamic performance of the aforementioned engine cycle, flight mach number and flight altitude are considered to be 2.5 and 30,000 m, respectively, due to the operational advantage of flying at ultrasonic altitude, and higher trust of hydrogen fuel. Accordingly, in the second phase, taking into account the mentioned flight conditions, an intelligent model has been obtained to predict output parameters (i.e. In the attained deep neural model, the HPC pressure ratio, fan pressure ratio, turbine Inlet temperature, intake air temperature, and bypass ratio are considered as input parameters. The provided datasets are randomly divided into two separate sets: the first set contains 6079 samples for model training and the second set contains 1520 samples for testing. Particularity, the Adam optimization algorithm, the cost function of the MSE, and the active function of Relu are used to train the network. The results show that the error percentage of the deep neural model is equal to 5.02%, 1.43%, and 2.92% in order to predict thrust, TSFC, and Overall exergetic efficiency, respectively, which indicates the success of the attained model in estimating the output parameters of the present problem. Introduction Gas turbines (GT) are one of the powers generation cycle types that is an internal combustion engine (ICE) of a rotary machine. These engines operate on the Brayton cycle (BC). Classically, the GTs have extensive applications in various industries ranging from oil, gas, and petrochemicals to power generation plants and various propulsion systems like airplane propulsion structures. The simplest GT engine configuration is Turbojet (TJ). In the TJs, the air is first entered into the compressor, then it enters the combustion chamber, after that, it increases its temperature and pressure, subsequently, it enters the turbine and it decreases its temperature and pressure.

We present a general framework for accurate positioning of sensors and end effectors in farm settings using a camera mounted on a robotic manipulator. Our main contribution is a visual servoing approach based on a new and robust feature tracking algorithm. Results from field experiments performed at an apple orchard demonstrate that our approach converges to a given termination criterion even under environmental influences such as strong winds, varying illumination conditions and partial occlusion of the target object. Further, we show experimentally that the system converges to the desired view for a wide range of initial conditions. This approach opens possibilities for new applications such as automated fruit inspection, fruit picking or precise pesticide application.

Artificial intelligence has deeply revolutionized the field of medicinal chemistry with many impressive applications, but the success of these applications requires a massive amount of training samples with high-quality annotations, which seriously limits the wide usage of data-driven methods. In this paper, we focus on the reaction yield prediction problem, which assists chemists in selecting high-yield reactions in a new chemical space only with a few experimental trials. To attack this challenge, we first put forth MetaRF, an attention-based differentiable random forest model specially designed for the few-shot yield prediction, where the attention weight of a random forest is automatically optimized by the meta-learning framework and can be quickly adapted to predict the performance of new reagents while given a few additional samples. To improve the few-shot learning performance, we further introduce a dimension-reduction based sampling method to determine valuable samples to be experimentally tested and then learned. Our methodology is evaluated on three different datasets and acquires satisfactory performance on few-shot prediction. In high-throughput experimentation (HTE) datasets, the average yield of our methodology's top 10 high-yield reactions is relatively close to the results of ideal yield selection.

Predicting mechanical properties in metal additive manufacturing (MAM) is vital to ensure the printed parts' performance, reliability, and whether they can fulfill requirements for a specific application. Conducting experiments to estimate mechanical properties in MAM processes, however, is a laborious and expensive task. Also, they can solely be designed for a particular material in a certain MAM process. Nonetheless, Machine learning (ML) methods, which are more flexible and cost-effective solutions, can be utilized to predict mechanical properties based on the processing parameters and material properties. To this end, in this work, a comprehensive framework for benchmarking ML for mechanical properties is introduced. An extensive experimental dataset is collected from more than 90 MAM articles and 140 MAM companies' data sheets containing MAM processing conditions, machines, materials, and resultant mechanical properties, including yield strength, ultimate tensile strength, elastic modulus, elongation, hardness as well as surface roughness. Physics-aware MAM featurization, adjustable ML models, and evaluation metrics are proposed to construct a comprehensive learning framework for mechanical properties prediction. Additionally, the Explainable AI method, i.e., SHAP analysis was studied to explain and interpret the ML models' predicted values for mechanical properties. Moreover, data-driven explicit models have been identified to estimate mechanical properties based on the processing parameters and material properties with more interpretability as compared to the employed ML models.

The agriculture sector is the foundation of any economy. However, with an increase in population, the agriculture sector will feel pressure and need to scale its supplies several times to cope with the increasing consumption. In addition, uncertain factors like climate change, diseases, and infertile land have propelled the sector to adopt innovative approaches like artificial intelligence to protect and increase crop yield. AI has the potential to change the agriculture sector by helping farmers minimize the risk of diseases, proactively adapt to changing climate conditions, monitor the security of crops using drones, etc., while keeping labor costs down (Figure 1). As a result, the overall AI in the agriculture market is projected to grow from an estimated $1B in 2020 to $4B by 2026, at a compound annual growth rate (CAGR) of 25.5% between 2020 and 2026. This series is about CV and DL for Industrial and Big Business Applications.

KAUST scientists have used deep learning algorithms to accelerate the examination of thousands of years old, giant, stone rectangles in the Saudi desert. "An international study showed that the huge, mysterious stone structures known as'Mustatil' (Arab word for'Rectangle') in northwestern Saudi Arabia, are among the oldest archeological ruins in the world," Saudi Minister of Culture, Prince Badr bin Abdullah bin Farhan, said in a tweet in 2021. These historic sites, which are around 7,000 years old, bewildered researchers and scientists who have long sought to determine their nature and the reasons behind their construction. A recent study by the University of Cambridge suggested that these huge structures, comprising chambers, entrances, and seats, are more complicated than expected. For quicker results, researchers at the King Abdullah University of Science and Technology (KAUST) have used an artificial intelligence network to carry out a detailed geological survey in the region, which hasn't been sufficiently studied so far.