… The fast development of deep learning has already … theory of successful deep learning has
yet to be clearly explained, and realization of state-of-the-art performance with deep learning …

… familiarity with programming, a basic understanding of computational performance issues,
complexity theory, introductory level calculus and some of the terminology of graph theory. …

… With the emergence of deep learning, AI-powered engineering wonders have entered our …
deep learning is still partial. This is one of the first books devoted to the theory of deep learning…

… deep learning theory. Alom et al. [9] give a survey of the techniques used in deep learning. …
complexity-based learning theory: the over-parameterization of deep learning makes almost …

… deep learning and its related fields, including deep supervised (eg, DNN, CNN, and RNN),
unsupervised (eg, AE, RBM, GAN) (sometimes GAN also used for semi-supervised learning …

… Many later non-neural methods of Artificial Intelligence and Machine Learning also learn
more and more abstract, hierarchical data representations. For example, syntactic pattern …

… We think that deep learning will have many more successes in the near future because it
requires very little engineering by hand, so it can easily take advantage of increases in the …

… A useful and popular meta-method to develop theory is decomposition. We first briefly …
machine learning, and then discuss how to decompose the theory of optimization for deep learning…

… deep learning, which has been receiving a lot of attention. The purpose is for readers to
understand deep learning … of technologies about deep learning: machine learning and computer …

… many layers deep. This book introduces a broad range of topics in relation to deep learning.
The … in linear algebra, probability theory and information theory, numerical computation, and …