Math and Architectures of Deep Learning

The mathematical paradigms that underlie deep learning typically start out as hard-to-read academic papers, often leaving engineers in the dark about how their models actually function.  Math and Architectures of Deep Learning bridges the gap between theory and practice, laying out the math of deep learning side by side with practical implementations in Python and PyTorch. Written by deep learning expert Krishnendu Chaudhury, you'll peer inside the “black box” to understand how your code is working, and learn to comprehend cutting-edge research you can turn into practical applications. about the technology It's important to understand how your deep learning models work, both so that you can maintain them efficiently and explain them to other stakeholders. Learning mathematical foundations and neural network architecture can be challenging, but the payoff is big. You'll be free from blind reliance on pre-packaged DL models and able to build, customize, and re-architect for your specific needs. And when things go wrong, you'll be glad you can quickly identify and fix problems. about the book Math and Architectures of Deep Learning sets out the foundations of DL in a way that's both useful and accessible to working practitioners. Each chapter explores a new fundamental DL concept or architectural pattern, explaining the underpinning mathematics and demonstrating how they work in practice with well-annotated Python code. You'll start with a primer of basic algebra, calculus, and statistics, working your way up to state-of-the-art DL paradigms taken from the latest research. By the time you're done, you'll have a combined theoretical insight and practical skills to identify and implement DL architecture for almost any real-world challenge.

Table of Contents:
table of contents READ IN LIVEBOOK 1AN OVERVIEW OF MACHINE LEARNING AND DEEP LEARNING READ IN LIVEBOOK 2INTRODUCTION TO VECTORS, MATRICES AND TENSORS FROM MACHINE LEARNING AND DATA SCIENCE POINT OF VIEW READ IN LIVEBOOK 3INTRODUCTION TO VECTOR CALCULUS FROM MACHINE LEARNING POINT OF VIEW READ IN LIVEBOOK 4LINEAR ALGEBRAIC TOOLS IN MACHINE LEARNING AND DATA SCIENCE READ IN LIVEBOOK 5PROBABILITY DISTRIBUTIONS FOR MACHINE LEARNING AND DATA SCIENCE READ IN LIVEBOOK 6BAYESIAN TOOLS FOR MACHINE LEARNING AND DATA SCIENCE READ IN LIVEBOOK 7FUNCTION APPROXIMATION: HOW NEURAL NETWORKS MODEL THE WORLD READ IN LIVEBOOK 8TRAINING NEURAL NETWORKS: FORWARD AND BACKPROPAGATION READ IN LIVEBOOK 9LOSS, OPTIMIZATION AND REGULARIZATION READ IN LIVEBOOK 10ONE, TWO AND THREE DIMENSIONAL CONVOLUTION AND TRANSPOSED CONVOLUTION IN NEURAL NETWORKS 11 IMAGE ANALYSIS: 2D CONVOLUTION BASED NEURAL NETWORK ARCHITECTURES FOR OBJECT RECOGNITION AND DETECTION 12 VIDEO ANALYSIS: 3D CONVOLUTION BASED SPATIO TEMPORAL NEURAL NETWORK ARCHITECTURES READ IN LIVEBOOK APPENDIX A: APPENDIX A.1Dot Product and cosine of the angle between two vectors A.2Computing variance of Gaussian Distribution A.3Two Theorems in Statistic