Textbook in PDF format

Artificial Intelligence (AI) revolves around creating and utilizing intelligent machines through science and engineering. This book delves into the theory and practical applications of Computer Science methods that incorporate AI across many domains. It covers techniques such as Machine Learning (ML), Convolutional Neural Networks (CNN), Deep Learning (DL), and Large Language Models (LLM) to tackle complex issues and overcome various challenges. From the Computer Science perspective, the core of Artificial Intelligence (AI) includes Machine Learning. In recent years the growth in utilizing AI applications has been exponential. One reason for this exponential growth has been the advancement in Machine Learning; many give credit for this advancement to Deep Learning (via Convolution Neural Networks, CNN) and new applications in Large Language Models (LLMs). This book covers the emerging trends in AI, Machine Learning, CNNs, and LLMs. Machine Learning methods heavily rely on large datasets. Although the topic of Data Science is not explicitly addressed in this book, many algorithms and methodologies that appear in this book utilize Data Science methodologies.

• Provides a comprehensive overview of the latest research in the field, as well as links to relevant references.
• Discusses Machine Learning (ML) and Large Language Models including GPT.
• Examines novel applications of AI in various domains. Preface Machine learning (ML) Detection of lesions in breast image using median filtering and convolutional neural networks Pushing the boundaries of probabilistic inference through message contraction optimization Facilitating cooperative missions through information sharing in heterogeneous agent teams Transferring knowledge: CNNs in Martian surface image classification Vascular system segmentation using deep learning Evolutionary CNN-based architectures with attention mechanisms for enhanced image classification Convolutional neural network (CNN) Multi-label concept detection in imaging entities of biomedical literature leveraging deep learning-based classification and object detection Revolutionizing supply chain dynamics: deep meta-learning and multi-task learning for enhanced predictive insights Characterization of Neuro-Symbolic AI and Graph Convolutional Network workloads Multivariant time series prediction using variants of LSTM deep neural networks Cellphone-based sUAS range estimation: a deep-learning classification and regression approach Automatic diagnosis of 12-lead ECG using DINOv2 Large language model (LLM) Leveraging linguistic features to improve machine learning models for detecting ChatGPT usage on exams Towards AI-augmented design space exploration pipelines for UAVs Improving subword embeddings in large language models using morphological information Swarm intelligence: a new software paradigm Leveraging large language models for efficient representation learning for entity resolution TOAA: Train once, apply anywhere