The use of autonomous underwater vehicles (AUVs) for surveying, mapping, and inspecting unexplored underwater areas plays a crucial role, where maneuverability and power efficiency are key factors for extending the use of these platforms, making six degrees of freedom (6-DOF) holonomic platforms essential tools. Although Proportional-Integral-Derivative (PID) and Model Predictive Control controllers are widely used in these applications, they often require accurate system knowledge, struggle with repeatability when facing payload or configuration changes, and can be time-consuming to fine-tune. While more advanced methods based on Deep Reinforcement Learning (DRL) have been proposed, they are typically limited to operating in fewer degrees of freedom. This paper proposes a novel DRL-based approach for controlling holonomic 6-DOF AUVs using the Truncated Quantile Critics (TQC) algorithm, which does not require manual tuning and directly feeds commands to the thrusters without prior knowledge of their configuration. Furthermore, it incorporates power consumption directly into the reward function. Simulation results show that the TQC High-Performance method achieves better performance to a fine-tuned PID controller when reaching a goal point, while the TQC Energy-Aware method demonstrates slightly lower performance but consumes 30% less power on average.

Robot-assisted feeding systems enhance the independence of individuals with motor impairments and alleviate caregiver burden. While existing systems predominantly rely on software-based safety features to mitigate risks during unforeseen collisions, this study explores the use of a mechanical fail-safe to improve safety. We designed a breakaway utensil attachment that decouples forces exerted by the robot on the user when excessive forces occur. Finite element analysis (FEA) simulations were performed to predict failure points under various loading conditions, followed by experimental validation using 3D-printed attachments with variations in slot depth and wall loops. To facilitate testing, a drop test rig was developed and validated. Our results demonstrated a consistent failure point at the slot of the attachment, with a slot depth of 1 mm and three wall loops achieving failure at the target force of 65 N. Additionally, the parameters can be tailored to customize the breakaway force based on user-specific factors, such as comfort and pain tolerance. CAD files and utensil assembly instructions can be found here: https://tinyurl.com/rfa-utensil-attachment

Traditional geological mapping methods, which rely on field observations and rock sample analysis, are ine fficient for continuous spatial mapping of geological features such as alteration zones. Deep learning models such as convolutional neural networks (CNNs) have ushered in a transformative era in remote sensing data analysis. CNNs excel in automatically extracting features from image data for classification and regression problems. CNNs have the ability to pinpoint specific mineralogical changes attributed to mineralisation processes by discerning subtle features within remote sensing data. Our methodology involves model training using two distinct sets of training samples generated through ground truth data and a fully automated approach through selective principal component analysis (PCA). We also compare CNNs with conventional machine learning models, including k-nearest neighbours, support vector machines, and multilayer perceptron. Our findings indicate that training with a ground truth-based dataset produces more reliable alteration maps. Additionally, we find that CNNs perform slightly better when compared to conventional machine learning models, which further demonstrates the ability of CNNs to capture spatial patterns in remote sensing data e ffectively. We find that Landsat 9 surpasses Landsat 8 in mapping iron oxide areas when employing the CNNs model trained with ground truth data obtained by field surveys. We also observe that using ASTER data with the CNNs model trained on the ground truth-based dataset produces the most accurate maps for two other important types of alteration zones, argillic and propylitic. This underscores the utility of CNNs in enhancing the e fficiency and precision of geological mapping, particularly in discerning subtle alterations indicative of mineralisation processes, especially those associated with critical metal resources. Introduction Geological maps are traditionally crafted through ground surveys and founded on field observations. They frequently incur inevitable errors due to the lack of spatial continuity of the field observations, thus yielding inaccurate representations (Campbell et al., 2005). Recognising these limitations, geologists have been prompted to seek innovative approaches and e fficient methodologies to accurately map geological features, particularly alteration zones (Kesler, 2007; McCuaig et al., 2010). The utilisation of remote sensing data for alteration mapping emerges as a pivotal technique in regional mineral exploration, enabling the precise spatial identification of alteration zones associated with mineralisation processes (Mohamed et al., 2021).

The aim of this thesis is to extend the applications of the Quantile Regression Forest (QRF) algorithm to handle mixed-frequency and longitudinal data. To this end, standard statistical approaches have been exploited to build two novel algorithms: the Mixed- Frequency Quantile Regression Forest (MIDAS-QRF) and the Finite Mixture Quantile Regression Forest (FM-QRF). The MIDAS-QRF combines the flexibility of QRF with the Mixed Data Sampling (MIDAS) approach, enabling non-parametric quantile estimation with variables observed at different frequencies. FM-QRF, on the other hand, extends random effects machine learning algorithms to a QR framework, allowing for conditional quantile estimation in a longitudinal data setting. The contributions of this dissertation lie both methodologically and empirically. Methodologically, the MIDAS-QRF and the FM-QRF represent two novel approaches for handling mixed-frequency and longitudinal data in QR machine learning framework. Empirically, the application of the proposed models in financial risk management and climate-change impact evaluation demonstrates their validity as accurate and flexible models to be applied in complex empirical settings.

As is now well understood, well trained ML model can provide insight to unlabeled or out of network data, without having to do time intensive experiments or use computationally expensive forward models. Our work is motivated by the continuum-scale modeling of materials physics, specifically using phase field methods to understand the phase dynamics and degradation effects of battery materials. Predictive phase field modeling of these processes relies on an accurate representation of the free energy density function. Historically, these free energies have been phenomenologically based which often can miss detailed physics such as high order interactions and complex phase dynamics needed to match with and explain experiments. With this background, we aimed to develop a framework enabling the creation of an atomistically informed free energy representation. The free energy densities can have compositions, order parameters, strains and temperature as arguments, attaining complex forms in the associated high-dimensional spaces. Therefore, we have employed ML models-specifically neural networks-in workflows that bridge first principles statistical mechanics and continuum scale models to represent the free energy density [4]. As an overview, our workflow uses density functional theory (DFT)-informed Monte Carlo (MC) to yield training data on generalized order parameter ηand chemical potentials µpairs.

Artificial intelligence (AI) has undergone remarkable development since the mid-2000s, particularly in the fields of machine learning and deep learning, driven by the explosive growth of large databases and computational capacity. Hungarian researchers recognized the significance of AI early on, actively participating in international research and achieving significant results in both theoretical and practical domains. This article presents some key achievements in Hungarian AI research. It highlights the results from the period before the rise of deep learning (the early 2010s), then discusses major theoretical advancements in Hungary after 2010. Finally, it provides a brief overview of AI-related applied scientific achievements from 2010 onward.

Strategic aggregation of electric vehicle batteries as energy reservoirs can optimize power grid demand, benefiting smart and connected communities, especially large office buildings that offer workplace charging. This involves optimizing charging and discharging to reduce peak energy costs and net peak demand, monitored over extended periods (e.g., a month), which involves making sequential decisions under uncertainty and delayed and sparse rewards, a continuous action space, and the complexity of ensuring generalization across diverse conditions. Existing algorithmic approaches, e.g., heuristic-based strategies, fall short in addressing real-time decision-making under dynamic conditions, and traditional reinforcement learning (RL) models struggle with large state-action spaces, multi-agent settings, and the need for long-term reward optimization. To address these challenges, we introduce a novel RL framework that combines the Deep Deterministic Policy Gradient approach (DDPG) with action masking and efficient MILP-driven policy guidance. Our approach balances the exploration of continuous action spaces to meet user charging demands. Using real-world data from a major electric vehicle manufacturer, we show that our approach comprehensively outperforms many well-established baselines and several scalable heuristic approaches, achieving significant cost savings while meeting all charging requirements. Our results show that the proposed approach is one of the first scalable and general approaches to solving the V2B energy management challenge.

This paper presents Phoeni6, a systematic approach for assessing the energy consumption of neural networks while upholding the principles of fair comparison and reproducibility. The methodology automates energy evaluations through containerized tools, robust database management, and versatile data models. In the first case study, the energy consumption of AlexNet and MobileNet was compared using raw and resized images. Results showed that MobileNet is up to 6.25% more energy-e fficient for raw images and 2.32% for resized datasets, while maintaining competitive accuracy levels. In the second study, the impact of image file formats on energy consumption was evaluated. BMP images reduced energy usage by up to 30% compared to PNG, highlighting the influence of file formats on energy e fficiency. These findings emphasize the importance of Phoeni6 in optimizing energy consumption for diverse neural network applications and establishing sustainable artificial intelligence practices. Introduction Deep Neural Networks (DNN) are being used with relative success in fields such as computer vision and natural language processing) [1, 2]. A growing number of initiatives have been promoting the development of these networks to solve everyday problems, including optimizing resource allocation in energy-constrained environments like wireless sensor networks [3]. There are repositories [4, 5] with hundreds of networks created and made available in lists ordered by accuracy, which is the primary metric used to assess the quality of each network. Their results emphasize that the search for energy efficiency can significantly benefit mobile devices' autonomy and positively a ff ect the financial costs and carbon footprints of large data centers distributed worldwide. These works measure energy to evaluate their technique. There is an evident global concern for the energy consumption of software products that a ffect people's daily lives--neural networks are becoming one of them. This fact has important implications on the criteria used to choose these products. It is reasonable to say that energy consumption is becoming part of the criteria for selecting neural networks, just as accuracy is. However, unlike the accuracy calculation, which fundamentally depends on the dataset and the procedures used during the training phase, the energy calculation depends on the devices involved. This aspect adds extra challenges to reproducing the results (RR) and making fair comparisons (FC) between di ff er-ent networks [24]. Evaluating the energy consumption of neural networks while adhering to the principles of Fair Comparison (FC) and Result Reproducibility (RR) presents significant challenges.

Motivated by reducing the computational and storage costs of LLMs, model compression and KV cache compression have attracted much attention from researchers. However, current methods predominantly emphasize maintaining the performance of compressed LLMs, as measured by perplexity or simple accuracy on tasks of common sense knowledge QA and basic arithmetic reasoning. In this blog, we present a brief review of recent advancements in LLMs related to retrieval-augmented generation, multi-step reasoning, external tools, and computational expressivity, all of which substantially enhance LLM performance. Then, we propose a lottery LLM hypothesis suggesting that for a given LLM and task, there exists a smaller lottery LLM capable of producing the same performance as the original LLM with the assistance of multi-step reasoning and external tools. Based on the review of current progress in LLMs, we discuss and summarize the essential capabilities that the lottery LLM and KV cache compression must possess, which are currently overlooked in existing methods.

Maximizing fusion performance in tokamaks relies on high energy confinement, often achieved through distinct operating regimes. The automated labeling of these confinement states is crucial to enable large-scale analyses or for real-time control applications. While this task becomes difficult to automate near state transitions or in marginal scenarios, much success has been achieved with data-driven models. However, these methods generally provide predictions as point estimates, and cannot adequately deal with missing and/or broken input signals. To enable wide-range applicability, we develop methods for confinement state classification with uncertainty quantification and model robustness. We focus on off-line analysis for TCV discharges, distinguishing L-mode, H-mode, and an in-between dithering phase (D). We propose ensembling data-driven methods on two axes: model formulations and feature sets. The former considers a dynamic formulation based on a recurrent Fourier Neural Operator-architecture and a static formulation based on gradient-boosted decision trees. These models are trained using multiple feature groupings categorized by diagnostic system or physical quantity. A dataset of 302 TCV discharges is fully labeled, and will be publicly released. We evaluate our method quantitatively using Cohen's kappa coefficient for predictive performance and the Expected Calibration Error for the uncertainty calibration. Furthermore, we discuss performance using a variety of common and alternative scenarios, the performance of individual components, out-of-distribution performance, cases of broken or missing signals, and evaluate conditionally-averaged behavior around different state transitions. Overall, the proposed method can distinguish L, D and H-mode with high performance, can cope with missing or broken signals, and provides meaningful uncertainty estimates.