In the last 5 years, the availability of large audio datasets in African countries has opened unlimited opportunities to build machine intelligence (MI) technologies that are closer to the people and speak, learn, understand, and do businesses in local languages, including for those who cannot read and write. Unfortunately, these audio datasets are not fully exploited by current MI tools, leaving several Africans out of MI business opportunities. Additionally, many state-of-the-art MI models are not culture-aware, and the ethics of their adoption indexes are questionable. The lack thereof is a major drawback in many applications in Africa. This paper summarizes recent developments in machine intelligence in Africa from a multi-layer multiscale and culture-aware ethics perspective, showcasing MI use cases in 54 African countries through 400 articles on MI research, industry, government actions, as well as uses in art, music, the informal economy, and small businesses in Africa. The survey also opens discussions on the reliability of MI rankings and indexes in the African continent as well as algorithmic definitions of unclear terms used in MI.

After the dataset collection stage, the preprocessing challenge, because of its numerous applications, such as audio surveillance, stage, and the NLP step, the classification process is carried out using E-learning, clinical studies, lie detection, entertainment, computer Bayesian Neural Networks. In the case of [6], the main purpose is to games and call centers [1]. Emotion processing is also important develop an application capable of analyzing the content of online for polarity detection which is very useful in social events, political courses and the contributions of their learners such as video transcriptions, movements and marketing campaigns [2]. Emotions play an important readings, questions and answers of the evaluation activities, posts role in our life, not only in human interaction, but also in decisionmaking in forums, etc. using NLP, to improve the teaching material and the processes, and in the perception of the world around us [3].

This work proposes DyExpert, a dynamic graph model for cross-domain link prediction. It can explicitly model historical evolving processes to learn the evolution pattern of a specific downstream graph and subsequently make pattern-specific link predictions. DyExpert adopts a decode-only transformer and is capable of efficiently parallel training and inference by \textit{conditioned link generation} that integrates both evolution modeling and link prediction. DyExpert is trained by extensive dynamic graphs across diverse domains, comprising 6M dynamic edges. Extensive experiments on eight untrained graphs demonstrate that DyExpert achieves state-of-the-art performance in cross-domain link prediction. Compared to the advanced baseline under the same setting, DyExpert achieves an average of 11.40% improvement Average Precision across eight graphs. More impressive, it surpasses the fully supervised performance of 8 advanced baselines on 6 untrained graphs.

Data-driven algorithm design is a paradigm that uses statistical and machine learning techniques to select from a class of algorithms for a computational problem an algorithm that has the best expected performance with respect to some (unknown) distribution on the instances of the problem. We build upon recent work in this line of research by introducing the idea where, instead of selecting a single algorithm that has the best performance, we allow the possibility of selecting an algorithm based on the instance to be solved. In particular, given a representative sample of instances, we learn a neural network that maps an instance of the problem to the most appropriate algorithm {\em for that instance}. We formalize this idea and derive rigorous sample complexity bounds for this learning problem, in the spirit of recent work in data-driven algorithm design. We then apply this approach to the problem of making good decisions in the branch-and-cut framework for mixed-integer optimization (e.g., which cut to add?). In other words, the neural network will take as input a mixed-integer optimization instance and output a decision that will result in a small branch-and-cut tree for that instance. Our computational results provide evidence that our particular way of using neural networks for cut selection can make a significant impact in reducing branch-and-cut tree sizes, compared to previous data-driven approaches.

Radio Frequency Energy Harvesting (RF-EH) networks are key enablers of massive Internet-ofthings by providing controllable and long-distance energy transfer to energy-limited devices. Relays, helping either energy or information transfer, have been demonstrated to significantly improve the performance of these networks. We first obtain the optimal solution to the scheduling and power control problem for the given relay selection. Then, the relay selection problem is formulated as a classification problem, for which two convolutional neural network (CNN) based architectures are proposed. While the first architecture employs conventional 2D convolution blocks and benefits from skip connections between layers; the second architecture replaces them with inception blocks, to decrease trainable parameter size without sacrificing accuracy for memory-constraint applications. To decrease the runtime complexity further, teacher-student learning is employed such that the teacher network is larger, and the student is a smaller size CNN-based architecture distilling the teacher's knowledge. A novel dichotomous searchbased algorithm is employed to determine the best architecture for the student network. Our simulation results demonstrate that the proposed solutions provide lower complexity than the state-of-art iterative approaches without compromising optimality. A. G. Onalan and S. Coleri are with the Department of Electrical and Electronics Engineering, and B.Kopru is with Department of Computer Engineering, Koc University, 34450, Istanbul, Turkey e-mail: {aonalan17, bkopru17, scoleri}@ku.edu.tr. Sinem Coleri acknowledges the support of the Scientific and Technological Research Council of Turkey 2247-A National Leaders Research Grant #121C314. Energy Harvesting (EH) is a promising alternative to fixed power supplies (e.g., batteries) for energy-constrained Internet-of-Things (IoT) applications, such as smart cities and wearable devices [1], by enabling the net-zero energy objective of sixth generation (6G) mobile networks [2]. The use cases and feasibility of wireless-powered IoT have been investigated in many standardization bodies, including IEEE 802.11 [3] and 3GPP [4]. Radio Frequency (RF) signals are preferred over other energy sources such as vibration and sun due to their independence from climate conditions, accessibility, and more predictable nature [5]. RF-EH network design follows two main protocols: Simultaneous Information and Power Transfer (SWIPT), in which power and information are sent simultaneously, and Wireless Powered Communication Networks (WPCN), in which power and information are sent consecutively in downlink (DL) and uplink (UL) [6].

Recently, large language models (LLMs) have shown remarkable capabilities including understanding context, engaging in logical reasoning, and generating responses. However, this is achieved at the expense of stringent computational and memory requirements, hindering their ability to effectively support long input sequences. This survey provides an inclusive review of the recent techniques and methods devised to extend the sequence length in LLMs, thereby enhancing their capacity for long-context understanding. In particular, we review and categorize a wide range of techniques including architectural modifications, such as modified positional encoding and altered attention mechanisms, which are designed to enhance the processing of longer sequences while avoiding a proportional increase in computational requirements. The diverse methodologies investigated in this study can be leveraged across different phases of LLMs, i.e., training, fine-tuning and inference. This enables LLMs to efficiently process extended sequences. The limitations of the current methodologies is discussed in the last section along with the suggestions for future research directions, underscoring the importance of sequence length in the continued advancement of LLMs.

Apart from what (little) OpenAI may be concealing from us, we all know (roughly) how ChatGPT works (its huge text database, its statistics, its vector representations, and their huge number of parameters, its next-word training, and so on). But none of us can say (hand on heart) that we are not surprised by what ChatGPT has proved to be able to do with these resources. This has even driven some of us to conclude that ChatGPT actually understands. It is not true that it understands. But it is also not true that we understand how it can do what it can do. I will suggest some hunches about benign biases: convergent constraints that emerge at LLM scale that may be helping ChatGPT do so much better than we would have expected. These biases are inherent in the nature of language itself, at LLM scale, and they are closely linked to what it is that ChatGPT lacks, which is direct sensorimotor grounding to connect its words to their referents and its propositions to their meanings. These convergent biases are related to (1) the parasitism of indirect verbal grounding on direct sensorimotor grounding, (2) the circularity of verbal definition, (3) the mirroring of language production and comprehension, (4) iconicity in propositions at LLM scale, (5) computational counterparts of human categorical perception in category learning by neural nets, and perhaps also (6) a conjecture by Chomsky about the laws of thought. The exposition will be in the form of a dialogue with ChatGPT-4.

Most existing federated learning (FL) methodologies have assumed training begins from a randomly initialized model. Recently, several studies have empirically demonstrated that leveraging a pre-trained model can offer advantageous initializations for FL. In this paper, we propose a collaborative pre-training approach, CoPreFL, which strategically designs a pre-trained model to serve as a good initialization for any downstream FL task. The key idea of our pre-training algorithm is a meta-learning procedure which mimics downstream distributed scenarios, enabling it to adapt to any unforeseen FL task. CoPreFL's pre-training optimization procedure also strikes a balance between average performance and fairness, with the aim of addressing these competing challenges in downstream FL tasks through intelligent initializations. Extensive experimental results validate that our pre-training method provides a robust initialization for any unseen downstream FL task, resulting in enhanced average performance and more equitable predictions.

The use of social network theory and methods of analysis have been applied to different domains in recent years, including public health. The complete procedure for carrying out a social network analysis (SNA) is a time-consuming task that entails a series of steps in which the expert in social network analysis could make mistakes. This research presents a multi-domain knowledge model capable of automatically gathering data and carrying out different social network analyses in different domains, without errors and obtaining the same conclusions that an expert in SNA would obtain. The model is represented in an ontology called OntoSNAQA, which is made up of classes, properties and rules representing the domains of People, Questionnaires and Social Network Analysis. Besides the ontology itself, different rules are represented by SWRL and SPARQL queries. A Knowledge Based System was created using OntoSNAQA and applied to a real case study in order to show the advantages of the approach. Finally, the results of an SNA analysis obtained through the model were compared to those obtained from some of the most widely used SNA applications: UCINET, Pajek, Cytoscape and Gephi, to test and confirm the validity of the model.

Recent advancements in large language models (LLMs) have provided a new avenue for chatbot development, while most existing research has primarily centered on single-user chatbots that focus on deciding "What" to answer after user inputs. In this paper, we identified that multi-user chatbots have more complex 3W design dimensions -- "What" to say, "When" to respond, and "Who" to answer. Additionally, we proposed Multi-User Chat Assistant (MUCA), which is an LLM-based framework for chatbots specifically designed for group discussions. MUCA consists of three main modules: Sub-topic Generator, Dialog Analyzer, and Utterance Strategies Arbitrator. These modules jointly determine suitable response contents, timings, and the appropriate recipients. To make the optimizing process for MUCA easier, we further propose an LLM-based Multi-User Simulator (MUS) that can mimic real user behavior. This enables faster simulation of a conversation between the chatbot and simulated users, making the early development of the chatbot framework much more efficient. MUCA demonstrates effectiveness, including appropriate chime-in timing, relevant content, and positive user engagement, in goal-oriented conversations with a small to medium number of participants, as evidenced by case studies and experimental results from user studies.