Introduction to deep learning using R : a step-by-step guide to learning and implementing deep learning models using R.

At a Glance; Contents; About the Author; About the Technical Reviewer; Acknowledgments; Introduction; Chapter 1: Introduction to Deep Learning; Deep Learning Models; Single Layer Perceptron Model (SLP); Multilayer Perceptron Model (MLP); Convolutional Neural Networks (CNNs); Recurrent Neural Networks (RNNs); Restricted Boltzmann Machines (RBMs); Deep Belief Networks (DBNs); Other Topics Discussed; Experimental Design; Feature Selection; Applied Machine Learning and Deep Learning; History of Deep Learning; Summary; Chapter 2: Mathematical Review; Statistical Concepts; Probability

And vs. OrBayes' Theorem; Random Variables; Variance; Standard Deviation; Coefficient of Determination (R Squared); Mean Squared Error (MSE); Linear Algebra; Scalars and Vectors; Properties of Vectors; Addition; Subtraction; Element Wise Multiplication; Axioms; Associative Property; Commutative Property; Identity Element of Addition; Inverse Elements of Addition; Identity Element of Scalar Multiplication; Distributivity of Scalar Multiplication with Respect to Vector Addition; Distributivity of Scalar Multiplication with Respect to Field Addition; Subspaces; Matrices; Matrix Properties

AdditionScalar Multiplication; Transposition; Types of Matrices; Matrix Multiplication; Scalar Multiplication; Matrix by Matrix Multiplication; Row and Column Vector Multiplication; Column Vector and Square Matrix; Square Matrices; Row Vector, Square Matrix, and Column Vector; Rectangular Matrices; Matrix Multiplication Properties (Two Matrices); Not Commutative; Distributive over Matrix Addition; Scalar Multiplication Is Compatible with Matrix Multiplication; Transpose; Trace; Norms; Euclidean Norm; L2 Norm; L1 Norm; P-norm; Matrix Norms; Inner Products; Norms on Inner Product Spaces; Proofs

OrthogonalityOuter Product; Eigenvalues and Eigenvectors; Linear Transformations; Quadratic Forms; Sylvester's Criterion; Orthogonal Projections; Range of a Matrix; Nullspace of a Matrix; Hyperplanes; Sequences; Properties of Sequences; Limits; Derivatives and Differentiability; Partial Derivatives and Gradients; Hessian Matrix; Summary; Chapter 3: A Review of Optimization and Machine Learning; Unconstrained Optimization; Local Minimizers; Global Minimizers; Conditions for Local Minimizers; Neighborhoods; Interior and Boundary Points; Machine Learning Methods: Supervised Learning

History of Machine LearningWhat Is an Algorithm?; Regression Models; Linear Regression; Ordinary Least Squares (OLS); Gradient Descent Algorithm; Multiple Linear Regression via Gradient Descent; Learning Rates; Choosing An Appropriate Learning Rate; Newton's Method; Levenberg-Marquardt Heuristic; What Is Multicollinearity?; Testing for Multicollinearity; Variance Inflation Factor (VIF); Ridge Regression; Least Absolute Shrinkage and Selection Operator (LASSO); Comparing Ridge Regression and LASSO; Evaluating Regression Models; Coefficient of Determination (R 2); Mean Squared Error (MSE)