Anis Koubaa

The predominance of English and Latin-based large language models (LLMs) has led to a notable deficit in native Arabic LLMs. This discrepancy is accentuated by the prevalent inclusion of English tokens in existing Arabic models, detracting from their efficacy in processing native Arabic's intricate morphology and syntax. Consequently, there is a theoretical and practical imperative for developing LLMs predominantly focused on Arabic linguistic elements. To address this gap, this paper proposes… عرض المزيد

The predominance of English and Latin-based large language models (LLMs) has led to a notable deficit in native Arabic LLMs. This discrepancy is accentuated by the prevalent inclusion of English tokens in existing Arabic models, detracting from their efficacy in processing native Arabic's intricate morphology and syntax. Consequently, there is a theoretical and practical imperative for developing LLMs predominantly focused on Arabic linguistic elements. To address this gap, this paper proposes ArabianGPT, a series of transformer-based models within the ArabianLLM suite designed explicitly for Arabic. These models, including ArabianGPT-0.1B and ArabianGPT-0.3B, vary in size and complexity, aligning with the nuanced linguistic characteristics of Arabic. The AraNizer tokenizer, integral to these models, addresses the unique morphological aspects of Arabic script, ensuring more accurate text processing. Empirical results from fine-tuning the models on tasks like sentiment analysis and summarization demonstrate significant improvements. For sentiment analysis, the fine-tuned ArabianGPT-0.1B model achieved a remarkable accuracy of 95%, a substantial increase from the base model's 56%. Similarly, in summarization tasks, fine-tuned models showed enhanced F1 scores, indicating improved precision and recall in generating concise summaries. Comparative analysis of fine-tuned ArabianGPT models against their base versions across various benchmarks reveals nuanced differences in performance, with fine-tuning positively impacting specific tasks like question answering and summarization. These findings underscore the efficacy of fine-tuning in aligning ArabianGPT models more closely with specific NLP tasks, highlighting the potential of tailored transformer architectures in advancing Arabic NLP. عرض أقل

Choosing the appropriate deployment strategy for any Deep Learning (DL) project in a production environment has always been the most challenging problem for industrial practitioners. There are several conflicting constraints and controversial approaches when it comes to deployment. Among these problems, the deployment on cloud versus the deployment on edge represents a common dilemma. In a nutshell, each approach provides benefits where the other would have limitations. This paper presents a… عرض المزيد

Choosing the appropriate deployment strategy for any Deep Learning (DL) project in a production environment has always been the most challenging problem for industrial practitioners. There are several conflicting constraints and controversial approaches when it comes to deployment. Among these problems, the deployment on cloud versus the deployment on edge represents a common dilemma. In a nutshell, each approach provides benefits where the other would have limitations. This paper presents a real-world case study on deploying a face recognition application using MTCNN detector and FaceNet recognizer. We report the challenges faced to decide on the best deployment strategy. We propose three inference architectures for the deployment, including cloud-based, edge-based, and hybrid. Furthermore, we evaluate the performance of face recognition inference on different cloud-based and edge-based GPU platforms. We consider different models of Jetson boards for the edge (Nano, TX2, Xavier NX, Xavier AGX) and various GPUs for the cloud (GTX 1080, RTX 2080Ti, RTX 2070, and RTX 8000). We also investigate the effect of deep learning model optimization using TensorRT and TFLite compared to a standard Tensorflow GPU model, and the effect of input resolution. We provide a benchmarking study for all these devices in terms of frames per second, execution times, energy and memory usages. After conducting a total of 294 experiments, the results demonstrate that the TensorRT optimization provides the fastest execution on all cloud and edge devices, at the expense of significantly larger energy consumption (up to +40% and +35% for edge and cloud devices, respectively, compared to Tensorflow). Whereas TFLite is the most efficient framework in terms of memory and power consumption, while providing significantly less (-4% to -62%) processing acceleration than TensorRT. عرض أقل

In the sixth volume of the successful Robot Operating System (ROS) work including carefully edited chapters devoted to the Robot Operating System (ROS) with working examples, demonstrations, and illustrations

Provides comprehensive coverage of the Robot Operating Systems (ROS), which is currently considered as the main development framework for robotics applications

Includes supplementary material representing all the code provided by the authors, which is available as open source… عرض المزيد

In the sixth volume of the successful Robot Operating System (ROS) work including carefully edited chapters devoted to the Robot Operating System (ROS) with working examples, demonstrations, and illustrations

Provides comprehensive coverage of the Robot Operating Systems (ROS), which is currently considered as the main development framework for robotics applications

Includes supplementary material representing all the code provided by the authors, which is available as open source in a Code repository

Covers areas related to robot development using ROS including robot navigation, UAVs, arm manipulation, multi-robot communication protocols, web and mobile interfaces, integration of new robotic platform, computer vision applications, and development of a real-world application and education عرض أقل

Unmanned Aerial Vehicles (UAVs) have been very effective in collecting aerial images data for various Internet-of-Things (IoT)/smart cities applications such as search and rescue, surveillance, vehicle detection, counting, intelligent transportation systems, to name a few. However, the real-time processing of collected data on edge in the context of the Internet-of-Drones remains an open challenge because UAVs have limited energy capabilities, while computer vision techniquesconsume excessive… عرض المزيد

Unmanned Aerial Vehicles (UAVs) have been very effective in collecting aerial images data for various Internet-of-Things (IoT)/smart cities applications such as search and rescue, surveillance, vehicle detection, counting, intelligent transportation systems, to name a few. However, the real-time processing of collected data on edge in the context of the Internet-of-Drones remains an open challenge because UAVs have limited energy capabilities, while computer vision techniquesconsume excessive energy and require abundant resources. This fact is even more critical when deep learning algorithms, such as convolutional neural networks (CNNs), are used for classification and detection. In this paper, we first propose a system architecture of computation offloading for Internet-connected drones. Then, we conduct a comprehensive experimental study to evaluate the performance in terms of energy, bandwidth, and delay of the cloud computation offloading approach versus the edge computing approach of deep learning applications in the context of UAVs. In particular, we investigate the tradeoff between the communication cost and the computation of the two candidate approaches experimentally. The main results demonstrate that the computation offloading approach allows us to provide much higher throughput (i.e., frames per second) as compared to the edge computing approach, despite the larger communication delays. عرض أقل

The objective of this book is to provide the reader with a comprehensive coverage on the Robot Operating Systems (ROS) and latest related systems, which is currently considered as the main development framework for robotics applications.
The book includes twenty-seven chapters organized into eight parts. Part 1 presents the basics and foundations of ROS. In Part 2, four chapters deal with navigation, motion and planning. Part 3 provides four examples of service and experimental robots. Part… عرض المزيد

The objective of this book is to provide the reader with a comprehensive coverage on the Robot Operating Systems (ROS) and latest related systems, which is currently considered as the main development framework for robotics applications.
The book includes twenty-seven chapters organized into eight parts. Part 1 presents the basics and foundations of ROS. In Part 2, four chapters deal with navigation, motion and planning. Part 3 provides four examples of service and experimental robots. Part 4 deals with real-world deployment of applications. Part 5 presents signal-processing tools for perception and sensing. Part 6 provides software engineering methodologies to design complex software with ROS. Simulations frameworks are presented in Part 7. Finally, Part 8 presents advanced tools and frameworks for ROS including multi-master extension, network introspection, controllers and cognitive systems.
This book will be a valuable companion for ROS users and developers to learn more ROS capabilities and features. عرض أقل