Introduction to Deep Learning: From Logical Calculus to Artifi...

Discover the fundamentals of deep learning with this engaging and accessible textbook, designed to provide a clear introduction to the current state-of-the-art connectionist models. Perfect for students and professionals alike, it offers a comprehensive overview of popular algorithms and architectures presented in a simple, intuitive style. The book explains complex mathematical derivations step-by-step, making advanced concepts easier to grasp.

The content covers a wide range of topics essential to understanding deep learning. It includes detailed discussions on convolutional networks, LSTMs, Word2vec, Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), neural Turing machines, memory networks, and autoencoders. Throughout the book, numerous examples are provided in working Python code, which is also available separately on an accompanying website for practical reference.

This textbook begins by introducing the fundamentals of machine learning, along with the necessary mathematical and computational prerequisites for deep learning. It explores feed-forward neural networks and discusses modifications applicable to any neural network architecture. The book also examines convolutional neural networks and the integration of recurrent connections into feed-forward models, providing a thorough understanding of these advanced structures.

Further topics include the concept of distributed representations, the autoencoder, and language processing with deep learning techniques. Additionally, it offers a brief history of artificial intelligence and neural networks, along with a review of interesting open research problems in the field. This comprehensive coverage makes it a valuable resource for those interested in the theoretical and practical aspects of deep learning.

This clearly written and lively primer on deep learning is an essential resource for graduate and advanced undergraduate students in computer science, cognitive science, and mathematics. It also benefits readers in fields such as linguistics, logic, philosophy, and psychology, providing a solid foundation for understanding the rapidly evolving landscape of artificial intelligence and connectionist models.

• Brand: Springer
• Product Type: ABIS_BOOK
• Title Series: Undergraduate Topics in Computer Science
• Genre: Mathematics
• Author: Sandro Skansi
• Binding: Paperback
• Language: English
• Publication Date: 2018