← Parminces
Goodfellow, Bengio & Courville, 2016

Deep Learning

The definitive textbook on deep learning, from mathematical foundations through core architectures. Every chapter condensed into interactive lessons with live simulations.

10
Chapters
30+
Simulations
80+
Quizzes
Part I: Applied Mathematics and Machine Learning Basics
Chapter 2

Linear Algebra

Scalars, vectors, matrices, tensors, eigendecomposition, SVD, the trace operator, and the determinant.

Chapter 3

Probability & Information Theory

Random variables, probability distributions, Bayes' rule, expectation, variance, common distributions, and information theory.

Chapter 4

Numerical Computation

Overflow, underflow, gradient-based optimization, Jacobians, Hessians, constrained optimization, and linear least squares.

Chapter 5

Machine Learning Basics

Learning algorithms, capacity, overfitting, underfitting, estimators, bias-variance, MLE, Bayesian statistics, SGD, and the curse of dimensionality.

Part II: Deep Networks — Modern Practice
Chapter 6

Deep Feedforward Networks

XOR problem, hidden layers, activation functions, output units, backpropagation, and universal approximation.

Chapter 7

Regularization

Parameter norm penalties, dataset augmentation, noise robustness, early stopping, dropout, and batch normalization.

Chapter 8

Optimization

SGD, momentum, learning rate schedules, adaptive methods (Adam, RMSProp), batch normalization, and loss surfaces.

Chapter 9

Convolutional Networks

Convolution operation, motivation, pooling, variants, efficient algorithms, and neuroscientific basis.

Chapter 10

Recurrence & Sequence Modeling

Unfolding graphs, RNNs, bidirectional RNNs, encoder-decoder, deep recurrent nets, LSTM, and GRU.

Chapter 11

Practical Methodology

Performance metrics, baselines, hyperparameter selection, debugging strategies, and when to gather more data.

Chapter 12

Applications

Large-scale deep learning, computer vision, speech recognition, NLP, recommender systems, and other applications.