Artificial Intelligence (AI) is revolutionizing various fields, including public health surveillance. In Africa, where health systems frequently encounter challenges such as limited resources, inadequate infrastructure, failed health information systems and a shortage of skilled health professionals, AI offers a transformative opportunity. This paper investigates the applications of AI in public health surveillance across the continent, presenting successful case studies and examining the benefits, opportunities, and challenges of implementing AI technologies in African healthcare settings. Our paper highlights AI's potential to enhance disease monitoring and health outcomes, and support effective public health interventions. The findings presented in the paper demonstrate that AI can significantly improve the accuracy and timeliness of disease detection and prediction, optimize resource allocation, and facilitate targeted public health strategies. Additionally, our paper identified key barriers to the widespread adoption of AI in African public health systems and proposed actionable recommendations to overcome these challenges.

In this work we present BOTS-LM, a series of bilingual language models proficient in both Setswana and English. Leveraging recent advancements in data availability and efficient fine-tuning, BOTS-LM achieves performance similar to models significantly larger than itself while maintaining computational efficiency. Our initial release features an 8 billion parameter generative large language model, with upcoming 0.5 billion and 1 billion parameter large language models and a 278 million parameter encoder-only model soon to be released. We find the 8 billion parameter model significantly outperforms Llama-3-70B and Aya 23 on English-Setswana translation tasks, approaching the performance of dedicated machine translation models, while approaching 70B parameter performance on Setswana reasoning as measured by a machine translated subset of the MMLU benchmark. To accompany the BOTS-LM series of language models, we release the largest Setswana web dataset, SetsText, totalling over 267 million tokens. In addition, we release the largest machine translated Setswana dataset, the first and largest synthetic Setswana dataset, training and evaluation code, training logs, and MMLU-tsn, a machine translated subset of MMLU.

This study analyzes hybrid AI systems' design patterns and their effectiveness in clinical decision-making using the boxology framework. It categorizes and copares various architectures combining machine learning and rule-based reasoning to provide insights into their structural foundations and healthcare applications. Addressing two main questions, how to categorize these systems againts established design patterns and how to extract insights through comparative analysis, the study uses design patterns from software engineering to understand and optimize healthcare AI systems. Boxology helps identify commonalities and create reusable solutions, enhancing these systems' scalability, reliability, and performance. Five primary architectures are examined: REML, MLRB, RBML, RMLT, and PERML. Each has unique strengths and weaknesses, highlighting the need for tailored approaches in clinical tasks. REML excels in high-accuracy prediction for datasets with limited data; MLRB in handling large datasets and complex data integration; RBML in explainability and trustworthiness; RMLT in managing high-dimensional data; and PERML, though limited in analysis, shows promise in urgent care scenarios. The study introduces four new patterns, creates five abstract categorization patterns, and refines those five further to specific systems. These contributions enhance Boxlogy's taxonomical organization and offer novel approaches to integrating expert knowledge with machine learning. Boxology's structured, modular apporach offers significant advantages in developing and analyzing hybrid AI systems, revealing commonalities, and promoting reusable solutions. In conclusion, this study underscores hybrid AI systems' crucial role in advancing healthcare and Boxology's potential to drive further innovation in AI integration, ultimately improving clinical decision support and patient outcomes.

Multilingual neural machine translation systems learn to map sentences of different languages into a common representation space. Intuitively, with a growing number of seen languages the encoder sentence representation grows more flexible and easily adaptable to new languages. In this work, we test this hypothesis by zero-shot translating from unseen languages. To deal with unknown vocabularies from unknown languages we propose a setup where we decouple learning of vocabulary and syntax, i.e. for each language we learn word representations in a separate step (using cross-lingual word embeddings), and then train to translate while keeping those word representations frozen. We demonstrate that this setup enables zero-shot translation from entirely unseen languages. Zero-shot translating with a model trained on Germanic and Romance languages we achieve scores of 42.6 BLEU for Portuguese-English and 20.7 BLEU for Russian-English on TED domain. We explore how this zero-shot translation capability develops with varying number of languages seen by the encoder. Lastly, we explore the effectiveness of our decoupled learning strategy for unsupervised machine translation. By exploiting our model's zero-shot translation capability for iterative back-translation we attain near parity with a supervised setting.

This paper introduces a novel two-stage framework for accurate Egyptian Vehicle License Plate Recognition (EVLPR). The first stage employs image processing techniques to reliably localize license plates, while the second stage utilizes a custom-designed deep learning model for robust Arabic character recognition. The proposed system achieves a remarkable 99.3% accuracy on a diverse dataset, surpassing existing approaches. Its potential applications extend to intelligent traffic management, including traffic violation detection and parking optimization. Future research will focus on enhancing the system's capabilities through architectural refinements, expanded datasets, and addressing system dependencies.

Abstract--Dynamic graphs (DG) are often used to describe evolving interactions between nodes in real-world applications. Temporal patterns are a natural feature of DGs and are also key to representation learning. However, existing dynamic GCN models are mostly composed of static GCNs and sequence modules, which results in the separation of spatiotemporal information and cannot effectively capture complex temporal patterns in DGs. To address this problem, this study proposes a spatial-temporal graph convolutional networks with diversified transformation (STGCNDT), which includes three aspects: a) constructing a unified graph tensor convolutional network (GTCN) using tensor M-products without the need to represent spatiotemporal information separately; b) introducing three transformation schemes in GTCN to model complex temporal patterns to aggregate temporal information; and c) constructing an ensemble of diversified transformation schemes to obtain higher representation capabilities. Empirical studies on four DGs that appear in communication networks show that the proposed STGCNDT significantly outperforms state-of-the-art models in solving link weight estimation tasks due to the diversified transformations.

Modern hardware architectures for Convolutional Neural Networks (CNNs), other than targeting high performance, aim at dissipating limited energy. Reducing the data movement cost between the computing cores and the memory is a way to mitigate the energy consumption. Systolic arrays are suitable architectures to achieve this objective: they use multiple processing elements that communicate each other to maximize data utilization, based on proper dataflows like the weight stationary and row stationary. Motivated by this, we have proposed TrIM, an innovative dataflow based on a triangular movement of inputs, and capable to reduce the number of memory accesses by one order of magnitude when compared to state-of-the-art systolic arrays. In this paper, we present a TrIM-based hardware architecture for CNNs. As a showcase, the accelerator is implemented onto a Field Programmable Gate Array (FPGA) to execute the VGG-16 CNN. The architecture achieves a peak throughput of 453.6 Giga Operations per Second, outperforming a state-of-the-art row stationary systolic array by ~5.1x in terms of memory accesses, and being up to ~12.2x more energy-efficient than other FPGA accelerators.

Federated learning (FL) involves several clients that share with a fusion center (FC), the model each client has trained with its own data. Conventional FL, which can be interpreted as an estimation or distortion-based approach, ignores the final use of model information (MI) by the FC and the other clients. In this paper, we introduce a novel FL framework in which the FC uses an aggregate version of the MI to make decisions that affect the client's utility functions. Clients cannot choose the decisions and can only use the MI reported to the FC to maximize their utility. Depending on the alignment between the client and FC utilities, the client may have an individual interest in adding strategic noise to the model. This general framework is stated and specialized to the case of clustering, in which noisy cluster representative information is reported. This is applied to the problem of power consumption scheduling. In this context, utility non-alignment occurs, for instance, when the client wants to consume when the price of electricity is low, whereas the FC wants the consumption to occur when the total power is the lowest. This is illustrated with aggregated real data from Ausgrid \cite{ausgrid}. Our numerical analysis clearly shows that the client can increase his utility by adding noise to the model reported to the FC. Corresponding results and source codes can be downloaded from \cite{source-code}.

Large language models (LLMs) have shown success in handling simple games with imperfect information and enabling multi-agent coordination, but their ability to facilitate practical collaboration against other agents in complex, imperfect information environments, especially in a non-English environment, still needs to be explored. This study investigates the applicability of knowledge acquired by open-source and API-based LLMs to sophisticated text-based games requiring agent collaboration under imperfect information, comparing their performance to established baselines using other types of agents. We propose a Theory of Mind (ToM) planning technique that allows LLM agents to adapt their strategy against various adversaries using only game rules, current state, and historical context as input. An external tool was incorporated to mitigate the challenge of dynamic and extensive action spaces in this card game. Our results show that although a performance gap exists between current LLMs and state-of-the-art reinforcement learning (RL) models, LLMs demonstrate ToM capabilities in this game setting. It consistently improves their performance against opposing agents, suggesting their ability to understand the actions of allies and adversaries and establish collaboration with allies. To encourage further research and understanding, we have made our codebase openly accessible.

Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely, training and test data do not cover the same set of data modalities. Traditional approaches for CMKD are based on a teacher/student paradigm where a teacher is trained on multi-modal data with the aim to successively distill knowledge from a multi-modal teacher to a single-modal student. Despite the widespread adoption of such paradigm, recent research has highlighted its inherent limitations in the context of cross-modal knowledge transfer.Taking a step beyond the teacher/student paradigm, here we introduce a new framework for cross-modal knowledge distillation, named DisCoM-KD (Disentanglement-learning based Cross-Modal Knowledge Distillation), that explicitly models different types of per-modality information with the aim to transfer knowledge from multi-modal data to a single-modal classifier. To this end, DisCoM-KD effectively combines disentanglement representation learning with adversarial domain adaptation to simultaneously extract, foreach modality, domain-invariant, domain-informative and domain-irrelevant features according to a specific downstream task. Unlike the traditional teacher/student paradigm, our framework simultaneously learns all single-modal classifiers, eliminating the need to learn each student model separately as well as the teacher classifier. We evaluated DisCoM-KD on three standard multi-modal benchmarks and compared its behaviourwith recent SOTA knowledge distillation frameworks. The findings clearly demonstrate the effectiveness of DisCoM-KD over competitors considering mismatch scenarios involving both overlapping and non-overlapping modalities. These results offer insights to reconsider the traditional paradigm for distilling information from multi-modal data to single-modal neural networks.