A project-based guide to the basics of deep learning.
This concise, project-driven guide to deep learning immerses readers in a series of practical programming projects designed to illuminate the application of deep learning across diverse areas of artificial intelligence, including computer vision, natural-language processing, and reinforcement learning. Authored by a seasoned artificial intelligence researcher specializing in natural-language processing, the book systematically covers fundamental concepts and techniques. Readers will explore feed-forward neural nets, convolutional neural nets, word embeddings, recurrent neural nets, sequence-to-sequence learning, deep reinforcement learning, and unsupervised models. By actively engaging with programs in Tensorflow, an open-source machine learning framework, students and practitioners alike will gain a hands-on understanding of deep learning strategies. The author's philosophy, "I find I learn computer science material best by sitting down and writing programs," underscores the book's practical, experiential approach, ensuring a deeper and more intuitive grasp of the subject matter.
Each chapter incorporates a programming project to solidify learning, exercises to test comprehension, and references for further exploration. An introductory chapter is dedicated to Tensorflow and its seamless integration with Python, a widely adopted programming language. A foundation in linear algebra, multivariate calculus, and probability and statistics is expected, alongside a basic familiarity with Python programming. This resource is suitable for both undergraduate and graduate courses, while practitioners will value it as an essential reference for implementing effective deep learning strategies.
