Deep neural networks are largely used for complex prediction tasks. There is plenty of empirical evidence of their successful end-to-end training for a diversity of tasks. Success is often measured based solely on the final performance of the trained network, and explanations on when, why and how they work are less emphasized. In this paper we study encoder-decoder recurrent neural networks with attention mechanisms for the task of reading handwritten chess scoresheets. Rather than prediction performance, our concern is to better understand how learning occurs in these type of networks. We characterize the task in terms of three subtasks, namely input-output alignment, sequential pattern recognition, and handwriting recognition, and experimentally investigate which factors affect their learning. We identify competition, collaboration and dependence relations between the subtasks, and argue that such knowledge might help one to better balance factors to properly train a network.

In recent times, there has been a growing interest in utilizing personalized large models on low-spec devices, such as mobile and CPU-only devices. However, utilizing a personalized large model in the on-device is inefficient, and sometimes limited due to computational cost. To tackle the problem, this paper presents the weights separation method to minimize on-device model weights using parameter-efficient fine-tuning methods. Moreover, some people speak multiple languages in an utterance, as known as code-switching, the personalized ASR model is necessary to address such cases. However, current multilingual speech recognition models are limited to recognizing a single language within each utterance. To tackle this problem, we propose code-switching speech recognition models that incorporate fine-tuned monolingual and multilingual speech recognition models. Additionally, we introduce a gated low-rank adaptation(GLoRA) for parameter-efficient fine-tuning with minimal performance degradation. Our experiments, conducted on Korean-English code-switching datasets, demonstrate that fine-tuning speech recognition models for code-switching surpasses the performance of traditional code-switching speech recognition models trained from scratch. Furthermore, GLoRA enhances parameter-efficient fine-tuning performance compared to conventional LoRA.

A graph is a fundamental data model to represent various entities and their complex relationships in society and nature, such as social networks, transportation networks, financial networks, and biomedical systems. Recently, large language models (LLMs) have showcased a strong generalization ability to handle various NLP and multi-mode tasks to answer users' arbitrary questions and specific-domain content generation. Compared with graph learning models, LLMs enjoy superior advantages in addressing the challenges of generalizing graph tasks by eliminating the need for training graph learning models and reducing the cost of manual annotation. In this survey, we conduct a comprehensive investigation of existing LLM studies on graph data, which summarizes the relevant graph analytics tasks solved by advanced LLM models and points out the existing remaining challenges and future directions. Specifically, we study the key problems of LLM-based generative graph analytics (LLM-GGA) with three categories: LLM-based graph query processing (LLM-GQP), LLM-based graph inference and learning (LLM-GIL), and graph-LLM-based applications. LLM-GQP focuses on an integration of graph analytics techniques and LLM prompts, including graph understanding and knowledge graph (KG) based augmented retrieval, while LLM-GIL focuses on learning and reasoning over graphs, including graph learning, graph-formed reasoning and graph representation. We summarize the useful prompts incorporated into LLM to handle different graph downstream tasks. Moreover, we give a summary of LLM model evaluation, benchmark datasets/tasks, and a deep pro and cons analysis of LLM models. We also explore open problems and future directions in this exciting interdisciplinary research area of LLMs and graph analytics.

This paper presents a software allowing to describe voices using a continuous Voice Femininity Percentage (VFP). This system is intended for transgender speakers during their voice transition and for voice therapists supporting them in this process. A corpus of 41 French cis- and transgender speakers was recorded. A perceptual evaluation allowed 57 participants to estimate the VFP for each voice. Binary gender classification models were trained on external gender-balanced data and used on overlapping windows to obtain average gender prediction estimates, which were calibrated to predict VFP and obtained higher accuracy than $F_0$ or vocal track length-based models. Training data speaking style and DNN architecture were shown to impact VFP estimation. Accuracy of the models was affected by speakers' age. This highlights the importance of style, age, and the conception of gender as binary or not, to build adequate statistical representations of cultural concepts.

The growth of competition in the telecommunications industry due to technological variety has facilitated the invention and expansion of new techniques for processing subscriber data to predict their behavior. Subscriber traffic represents all kinds of electronic data transmitted in the network [1]. This data is usually in the form of network flows passing from one node to another [2]. Furthermore, accurately predicting subscriber data can improve the Quality of Experience (QoE) to foresee and predict various anomalies, especially when the company faces revenue loss due to malicious activities. In addition, having the ability to forecast future data usage can be crucial for bandwidth sharing policy within the telecommunication business. Particularly, forecasting integrates a strong sense of seasonality towards data growth to enable management to better predict potential revenue and anomalies.

This paper presents Killkan, the first dataset for automatic speech recognition (ASR) in the Kichwa language, an indigenous language of Ecuador. Kichwa is an extremely low-resource endangered language, and there have been no resources before Killkan for Kichwa to be incorporated in applications of natural language processing. The dataset contains approximately 4 hours of audio with transcription, translation into Spanish, and morphosyntactic annotation in the format of Universal Dependencies. The audio data was retrieved from a publicly available radio program in Kichwa. This paper also provides corpus-linguistic analyses of the dataset with a special focus on the agglutinative morphology of Kichwa and frequent code-switching with Spanish. The experiments show that the dataset makes it possible to develop the first ASR system for Kichwa with reliable quality despite its small dataset size. This dataset, the ASR model, and the code used to develop them will be publicly available.

Pretrained language models underpin several AI applications, but their high computational cost for training limits accessibility. Initiatives such as BLOOM and StarCoder aim to democratize access to pretrained models for collaborative community development. However, such existing models face challenges: limited multilingual capabilities, continual pretraining causing catastrophic forgetting, whereas pretraining from scratch is computationally expensive, and compliance with AI safety and development laws. This paper presents Aurora-M, a 15B parameter multilingual open-source model trained on English, Finnish, Hindi, Japanese, Vietnamese, and code. Continually pretrained from StarCoderPlus on 435 billion additional tokens, Aurora-M surpasses 2 trillion tokens in total training token count. It is the first open-source multilingual model fine-tuned on human-reviewed safety instructions, thus aligning its development not only with conventional red-teaming considerations, but also with the specific concerns articulated in the Biden-Harris Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence. Aurora-M is rigorously evaluated across various tasks and languages, demonstrating robustness against catastrophic forgetting and outperforming alternatives in multilingual settings, particularly in safety evaluations. To promote responsible open-source LLM development, Aurora-M and its variants are released at https://huggingface.co/collections/aurora-m/aurora-m-models-65fdfdff62471e09812f5407 .

Mycotoxins are a group of naturally occurring, toxic chemical compounds produced by certain species of moulds (fungi), during growth on various crops and foodstuffs, including cereals, nuts, spices and dairy products (The World Health Organization (WHO), 2023). The ingestion of certain mycotoxins has been linked to a range of harmful health impacts on both humans and animals, from short-term poisoning to long-term consequences such as liver cancer, and in some cases, death (Mavrommatis et al., 2021; Marroquín-Cardona et al., 2014; Liu and Wu, 2010). Mycotoxins are secondary metabolites (that is, compounds produced by an organism that are not essential for its primary life processes) and are often produced during the pre-harvest, harvest, and storage phases under favourable conditions of humidity and temperature (Marroquín-Cardona et al., 2014; Van der Fels-Klerx et al., 2022). The most prevalent mycotoxins include aflatoxins, tricothecenes, fumonisins, zearalenones, ochratoxins and patulin, and are produced by certain plant-pathogenic species of Aspergillus, Fusarium, and Penicillium (Tola and Kebede, 2016). Mycotoxin contamination in crop products has been found to vary significantly across different geographical locations and is influenced by annual weather conditions (Logrieco et al., 2021; Leggieri et al., 2020).

Myocardial Infarction is a main cause of mortality globally, and accurate risk prediction is crucial for improving patient outcomes. Machine Learning techniques have shown promise in identifying high-risk patients and predicting outcomes. However, patient data often contain vast amounts of information and missing values, posing challenges for feature selection and imputation methods. In this article, we investigate the impact of the data preprocessing task and compare three ensembles boosted tree methods to predict the risk of mortality in patients with myocardial infarction. Further, we use the Tree Shapley Additive Explanations method to identify relationships among all the features for the performed predictions, leveraging the entirety of the available data in the analysis. Notably, our approach achieved a superior performance when compared to other existing machine learning approaches, with an F1-score of 91,2% and an accuracy of 91,8% for LightGBM without data preprocessing.

This work investigates the potential of Reinforcement Learning (RL) to tackle robot motion planning challenges in the dynamic RoboCup Small Size League (SSL). Using a heuristic control approach, we evaluate RL's effectiveness in obstacle-free and single-obstacle path-planning environments. Ablation studies reveal significant performance improvements. Our method achieved a 60% time gain in obstacle-free environments compared to baseline algorithms. Additionally, our findings demonstrated dynamic obstacle avoidance capabilities, adeptly navigating around moving blocks. These findings highlight the potential of RL to enhance robot motion planning in the challenging and unpredictable SSL environment.