Artificial Neural Networks: Methods and Applications
Year: 2024
Type: book-chapter
Abstract: This chapter provides a comprehensive overview of Artificial Neural Networks (ANNs), highlighting their methods and diverse applications. It begins with an introduction to the fundamental concepts and historical development of ANNs, tracing their evolution from early computational models to sophisticated deep learning algorithms. The core methodologies are examined in detail, including various neural network architectures such as Feedforward Neural Networks, Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs). Key learning algorithms like backpropagation and gradient descent, along with common activation functions, are discussed to elucidate how ANNs learn and process information. The chapter also explores the wide-ranging applications of ANNs, showcasing their transformative impact on fields such as image recognition, natural language processing (NLP), autonomous vehicles, healthcare, and financial services. Each application area is illustrated with examples of how ANNs solve complex problems and enhance technological capabilities. Furthermore, the chapter addresses the challenges facing ANN development, including data requirements, computational resources, and interpretability issues. It also outlines future directions in the field, emphasizing the potential of improved architectures, integration with emerging technologies, and the importance of ethical considerations in AI. Overall, this chapter aims to provide readers with a thorough understanding of the methods underpinning artificial neural networks and their significant applications, along with insights into the ongoing advancements and challenges in this dynamic field.
Authors: Balthilak A, Pathur Nisha S, Allocious Britto Rajkumar R
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Keywords: artificial neural networks, feedforward neural networks, convolutional neural networks, recurrent neural networks, backpropagation, gradient descent, activation functions, image recognition, natural language processing, autonomous vehicles, medical applications, financial services, data requirements, interpretability, AI ethics
Open Access status: green
OpenAlex ID: W6930386907
