Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, prompting interest in their application as black-box optimizers. This paper asserts that LLMs possess the capability for zero-shot optimization across diverse scenarios, including multi-objective and high-dimensional problems. We introduce a novel population-based method for numerical optimization using LLMs called Language-Model-Based Evolutionary Optimizer (LEO). Our hypothesis is supported through numerical examples, spanning benchmark and industrial engineering problems such as supersonic nozzle shape optimization, heat transfer, and windfarm layout optimization. We compare our method to several gradient-based and gradient-free optimization approaches. While LLMs yield comparable results to state-of-the-art methods, their imaginative nature and propensity to hallucinate demand careful handling. We provide practical guidelines for obtaining reliable answers from LLMs and discuss method limitations and potential research directions.

Fractional statistical moments are utilized for various tasks of uncertainty quantification, including the estimation of probability distributions. However, an estimation of fractional statistical moments of costly mathematical models by statistical sampling is challenging since it is typically not possible to create a large experimental design due to limitations in computing capacity. This paper presents a novel approach for the analytical estimation of fractional moments, directly from polynomial chaos expansions. Specifically, the first four statistical moments obtained from the deterministic PCE coefficients are used for an estimation of arbitrary fractional moments via H\"{o}lder's inequality. The proposed approach is utilized for an estimation of statistical moments and probability distributions in three numerical examples of increasing complexity. Obtained results show that the proposed approach achieves a superior performance in estimating the distribution of the response, in comparison to a standard Latin hypercube sampling in the presented examples.

In this study, a human evaluation is carried out on how hyperparameter settings impact the quality of Transformer-based Neural Machine Translation (NMT) for the low-resourced English--Irish pair. SentencePiece models using both Byte Pair Encoding (BPE) and unigram approaches were appraised. Variations in model architectures included modifying the number of layers, evaluating the optimal number of heads for attention and testing various regularisation techniques. The greatest performance improvement was recorded for a Transformer-optimized model with a 16k BPE subword model. Compared with a baseline Recurrent Neural Network (RNN) model, a Transformer-optimized model demonstrated a BLEU score improvement of 7.8 points. When benchmarked against Google Translate, our translation engines demonstrated significant improvements. Furthermore, a quantitative fine-grained manual evaluation was conducted which compared the performance of machine translation systems. Using the Multidimensional Quality Metrics (MQM) error taxonomy, a human evaluation of the error types generated by an RNN-based system and a Transformer-based system was explored. Our findings show the best-performing Transformer system significantly reduces both accuracy and fluency errors when compared with an RNN-based model.

The industry is rich in cases when we are required to make forecasting for large amounts of time series at once. However, we might be in a situation where we can not afford to train a separate model for each of them. Such issue in time series modeling remains without due attention. The remedy for this setting is the establishment of a foundation model. Such a model is expected to work in zero-shot and few-shot regimes. However, what should we take as a training dataset for such kind of model? Witnessing the benefits from the enrichment of NLP datasets with artificially-generated data, we might want to adopt their experience for time series. In contrast to natural language, the process of generation of synthetic time series data is even more favorable because it provides full control of series patterns, time horizons, and number of samples. In this work, we consider the essential question if it is advantageous to train a foundation model on synthetic data or it is better to utilize only a limited number of real-life examples. Our experiments are conducted only for regular time series and speak in favor of leveraging solely the real time series. Moreover, the choice of the proper source dataset strongly influences the performance during inference. When provided access even to a limited quantity of short time series data, employing it within a supervised framework yields more favorable results than training on a larger volume of synthetic data. The code for our experiments is publicly available on Github \url{https://github.com/sb-ai-lab/synthesize_or_not}.

Improving the safety of collaborative manipulators necessitates the reduction of inertia in the moving part. Within this paper, we introduce a novel approach in the form of a passive 3D wire aligner, serving as a lightweight and low-friction power transmission mechanism, thus achieving the desired low inertia in the manipulator's operation. Through the utilization of this innovation, the consolidation of hefty actuators onto the root link becomes feasible, consequently enabling a supple drive characterized by minimal friction. To demonstrate the efficacy of this device, we fabricate an ultralight 7 degrees of freedom (DoF) manipulator named SAQIEL, boasting a mere 1.5 kg weight for its moving components. Notably, to mitigate friction within SAQIEL's actuation system, we employ a distinctive mechanism that directly winds wires using motors, obviating the need for traditional gear or belt-based speed reduction mechanisms. Through a series of empirical trials, we substantiate that SAQIEL adeptly strikes balance between lightweight design, substantial payload capacity, elevated velocity, precision, and adaptability.

Advanced machine learning algorithms are increasingly utilized to provide data-based prediction and decision-making support in Industry 4.0. However, the prediction accuracy achieved by the existing models is insufficient to warrant practical implementation in real-world applications. This is because not all features present in real-world datasets possess a direct relevance to the predictive analysis being conducted. Consequently, the careful incorporation of select features has the potential to yield a substantial positive impact on the outcome. To address the research gap, this paper proposes a novel hybrid framework that combines the feature importance detector - local interpretable model-agnostic explanations (LIME) and the feature interaction detector - neural interaction detection (NID), to improve prediction accuracy. By applying the proposed framework, unnecessary features can be eliminated, and interactions are encoded to generate a more conducive dataset for predictive purposes. Subsequently, the proposed model is deployed to refine the prediction of electricity consumption in foundry processing. The experimental outcomes reveal an augmentation of up to 9.56% in the R2 score, and a diminution of up to 24.05% in the root mean square error.

Underwater soft grippers exhibit potential for applications such as monitoring, research, and object retrieval. However, existing underwater gripping techniques frequently cause disturbances to ecosystems. In response to this challenge, we present a novel underwater gripping framework comprising a lightweight gripper affixed to a custom submarine pod deployable via drone. This approach minimizes water disturbance and enables efficient navigation to target areas, enhancing overall mission effectiveness. The pod allows for underwater motion and is characterized by four degrees of freedom. It is provided with a custom buoyancy system, two water pumps for differential thrust and two for pitching. The system allows for buoyancy adjustments up to a depth of 6 meters, as well as motion in the plane. The 3-fingered gripper is manufactured out of silicone and was successfully tested on objects with different shapes and sizes, demonstrating a maximum pulling force of up to 8 N when underwater. The reliability of the submarine pod was tested in a water tank by tracking its attitude and energy consumption during grasping maneuvers. The system also accomplished a successful mission in a lake, where it was deployed on a hexacopter. Overall, the integration of this system expands the operational capabilities of underwater grasping, makes grasping missions more efficient and easy to automate, as well as causing less disturbance to the water ecosystem.

Google's AI programs are still generating woke and controversial answers despite the company claiming to have stripped Gemini of its liberal biases. The initial outrage began last month when the tech giant's image generator depicted historically inaccurate figures including Black Founding Fathers and ethnic minority Nazis in 1940s Germany. Google CEO Sundar Pichai described them as'completely unacceptable' and the company removed the software's ability to produce images this week as a form of damage control. In one of its most shocking answers, it could not tell us which was worse - 'dead-naming' a trans person or unleashing a pandemic on the world. Google's AI programs were accused of being ultra woke after depicting historically inaccurate figures including Black Founding Fathers Gemini also claimed that'neither option is acceptable' when asked whether burning fossil fuels or harvesting human blood was preferable.

The rapid advancement of Internet of Things (IoT) necessitates the development of optimized Chemiresistive Sensor (CRS) arrays that are both energy-efficient and capable. This study introduces a novel optimization strategy that employs a rapid ensemble learning-based model committee approach to achieve these goals. Utilizing machine learning models such as Elastic Net Regression, Random Forests, and XGBoost, among others, the strategy identifies the most impactful sensors in a CRS array for accurate classification: A weighted voting mechanism is introduced to aggregate the models' opinions in sensor selection, thereby setting up wo distinct working modes, termed "Blue" and "Green". The Blue mode operates with all sensors for maximum detection capability, while the Green mode selectively activates only key sensors, significantly reducing energy consumption without compromising detection accuracy. The strategy is validated through theoretical calculations and Monte Carlo simulations, demonstrating its effectiveness and accuracy. The proposed optimization strategy not only elevates the detection capability of CRS arrays but also brings it closer to theoretical limits, promising significant implications for the development of low-cost, easily fabricable next-generation IoT sensor terminals.

Neural network pruning serves as a critical technique for enhancing the efficiency of deep learning models. Unlike unstructured pruning, which only sets specific parameters to zero, structured pruning eliminates entire channels, thus yielding direct computational and storage benefits. However, the diverse patterns for coupling parameters, such as residual connections and group convolutions, the diverse deep learning frameworks, and the various time stages at which pruning can be performed make existing pruning methods less adaptable to different architectures, frameworks, and pruning criteria. To address this, we introduce Structurally Prune Anything (SPA), a versatile structured pruning framework that can prune neural networks with any architecture, from any framework, and at any stage of training. SPA leverages a standardized computational graph and ONNX representation to prune diverse neural network architectures without the need for manual intervention. SPA employs a group-level importance estimation method, which groups dependent computational operators, estimates their importance, and prunes unimportant coupled channels. This enables the transfer of various existing pruning criteria into a structured group style. As a result, SPA supports pruning at any time, either before training, after training with fine-tuning, or after training without fine-tuning. In the context of the latter, we introduce Optimal Brain SPA (OBSPA), an algorithm that achieves state-of-the-art pruning results needing neither fine-tuning nor calibration data. In extensive experiments, SPA shows competitive to state-of-the-art pruning performance across various architectures, from popular frameworks, at different pruning times.