Preliminaries

• 1.Data ManipulationPTTFJAXMX
• 2.Data PreprocessingPTTFJAXMX
• 3.Linear AlgebraPTTFJAXMX
• 4.CalculusPTTFJAXMX
• 5.Automatic DifferentiationPTTFJAXMX
• 6.Probability and StatisticsPTTFJAXMX
• 7.DocumentationPTTFJAXMX

Linear Neural Networks for Regression

• 1.Linear RegressionPTTFJAXMX
• 2.Object-Oriented Design for ImplementationPTTFJAXMX
• 3.Synthetic Regression DataPTTFJAXMX
• 4.Linear Regression Implementation from ScratchPTTFJAXMX
• 5.Concise Implementation of Linear RegressionPTTFJAXMX
• 6.Weight DecayPTTFJAXMX

Linear Neural Networks for Classification

• 1.The Image Classification DatasetPTTFJAXMX
• 2.The Base Classification ModelPTTFJAXMX
• 3.Softmax Regression Implementation from ScratchPTTFJAXMX
• 4.Concise Implementation of Softmax RegressionPTTFJAXMX

Multilayer Perceptrons

• 1.Multilayer PerceptronsPTTFJAXMX
• 2.Implementation of Multilayer PerceptronsPTTFJAXMX
• 3.Numerical Stability and InitializationPTTFJAXMX
• 4.DropoutPTTFJAXMX
• 5.Predicting House Prices on KagglePTTFJAXMX

Builders' Guide

• 1.Layers and ModulesPTTFJAXMX
• 2.Parameter ManagementPTTFJAXMX
• 3.Parameter InitializationPTTFJAXMX
• 4.Lazy InitializationPTTFJAXMX
• 5.Custom LayersPTTFJAXMX
• 6.File I/OPTTFJAXMX
• 7.GPUsPTTFJAXMX

Convolutional Neural Networks

• 1.Convolutions for ImagesPTTFJAXMX
• 2.Padding and StridePTTFJAXMX
• 3.Multiple Input and Multiple Output ChannelsPTTFJAXMX
• 4.PoolingPTTFJAXMX
• 5.Convolutional Neural Networks (LeNet)PTTFJAXMX

Modern Convolutional Neural Networks

• 1.Deep Convolutional Neural Networks (AlexNet)PTTFJAXMX
• 2.Networks Using Blocks (VGG)PTTFJAXMX
• 3.Network in Network (NiN)PTTFJAXMX
• 4.Multi-Branch Networks (GoogLeNet)PTTFJAXMX
• 5.Batch NormalizationPTTFJAXMX
• 6.Residual Networks (ResNet) and ResNeXtPTTFJAXMX
• 7.Densely Connected Networks (DenseNet)PTTFJAXMX
• 8.Designing Convolutional Network ArchitecturesPTTFJAXMX

Recurrent Neural Networks

• 1.Working with SequencesPTTFJAXMX
• 2.Converting Raw Text into Sequence DataPTTFJAXMX
• 3.Language ModelsPTTFJAXMX
• 4.Recurrent Neural NetworksPTTFJAXMX
• 5.Recurrent Neural Network Implementation from ScratchPTTFJAXMX
• 6.Concise Implementation of Recurrent Neural NetworksPTTFJAXMX

Modern Recurrent Neural Networks

• 1.Long Short-Term Memory (LSTM)PTTFJAXMX
• 2.Gated Recurrent Units (GRU)PTTFJAXMX
• 3.Deep Recurrent Neural NetworksPTTFJAXMX
• 4.Bidirectional Recurrent Neural NetworksPTTFJAXMX
• 5.Machine Translation and the DatasetPTTFJAXMX
• 6.The Encoder--Decoder ArchitecturePTTFJAXMX
• 7.Sequence-to-Sequence Learning for Machine TranslationPTTFJAXMX

Attention Mechanisms and Transformers

• 1.Queries, Keys, and ValuesPTTFJAXMX
• 2.Attention Pooling by SimilarityPTTFJAXMX
• 3.Attention Scoring FunctionsPTTFJAXMX
• 4.The Bahdanau Attention MechanismPTTFJAXMX
• 5.Multi-Head AttentionPTTFJAXMX
• 6.Self-Attention and Positional EncodingPTTFJAXMX
• 7.The Transformer ArchitecturePTTFJAXMX
• 8.Transformers for VisionPTTFJAXMX

Optimization Algorithms

• 1.Optimization and Deep LearningPTTFJAXMX
• 2.ConvexityPTTFJAXMX
• 3.Gradient DescentPTTFJAXMX
• 4.Stochastic Gradient DescentPTTFJAXMX
• 5.Minibatch Stochastic Gradient DescentPTTFJAXMX
• 6.MomentumPTTFJAXMX
• 7.AdagradPTTFJAXMX
• 8.RMSPropPTTFJAXMX
• 9.AdadeltaPTTFJAXMX
• 10.AdamPTTFJAXMX
• 11.Learning Rate SchedulingPTTFJAXMX

Computational Performance

• 1.Compilers and InterpretersPTTFJAXMX
• 2.Asynchronous ComputationPTTFJAXMX
• 3.Automatic ParallelismPTTFJAXMX
• 4.Training on Multiple GPUsPTTFJAXMX
• 5.Concise Implementation for Multiple GPUsPTTFJAXMX

Computer Vision

• 1.Image AugmentationPTTFJAXMX
• 2.Fine-TuningPTTFJAXMX
• 3.Object Detection and Bounding BoxesPTTFJAXMX
• 4.Anchor BoxesPTTFJAXMX
• 5.Multiscale Object DetectionPTTFJAXMX
• 6.The Object Detection DatasetPTTFJAXMX
• 7.Single Shot Multibox DetectionPTTFJAXMX
• 8.Region-based CNNs (R-CNNs)PTTFJAXMX
• 9.Semantic Segmentation and the DatasetPTTFJAXMX
• 10.Transposed ConvolutionPTTFJAXMX
• 11.Fully Convolutional NetworksPTTFJAXMX
• 12.Neural Style TransferPTTFJAXMX
• 13.Image Classification (CIFAR-10) on KagglePTTFJAXMX
• 14.Dog Breed Identification (ImageNet Dogs) on KagglePTTFJAXMX

Natural Language Processing: Pretraining

• 1.The Dataset for Pretraining Word EmbeddingsPTTFJAXMX
• 2.Pretraining word2vecPTTFJAXMX
• 3.Subword EmbeddingPTTFJAXMX
• 4.Word Similarity and AnalogyPTTFJAXMX
• 5.Bidirectional Encoder Representations from Transformers (BERT)PTTFJAXMX
• 6.The Dataset for Pretraining BERTPTTFJAXMX
• 7.Pretraining BERTPTTFJAXMX

Natural Language Processing: Applications

• 1.Sentiment Analysis and the DatasetPTTFJAXMX
• 2.Sentiment Analysis: Using Recurrent Neural NetworksPTTFJAXMX
• 3.Sentiment Analysis: Using Convolutional Neural NetworksPTTFJAXMX
• 4.Natural Language Inference and the DatasetPTTFJAXMX
• 5.Natural Language Inference: Using AttentionPTTFJAXMX
• 6.Natural Language Inference: Fine-Tuning BERTPTTFJAXMX

Reinforcement Learning

• 1.Markov Decision Process (MDP)PTTFJAXMX
• 2.Value IterationPTTFJAXMX
• 3.Q-LearningPTTFJAXMX

Gaussian Processes

• 1.Gaussian Process PriorsPTTFJAXMX
• 2.Gaussian Process InferencePTTFJAXMX

Hyperparameter Optimization

• 1.What Is Hyperparameter Optimization?PTTFJAXMX
• 2.Hyperparameter Optimization APIPTTFJAXMX
• 3.Asynchronous Random SearchPTTFJAXMX
• 4.Multi-Fidelity Hyperparameter OptimizationPTTFJAXMX
• 5.Asynchronous Successive HalvingPTTFJAXMX

Generative Adversarial Networks

• 1.Generative Adversarial NetworksPTTFJAXMX
• 2.Deep Convolutional Generative Adversarial NetworksPTTFJAXMX

Recommender Systems

• 1.The MovieLens DatasetPTTFJAXMX
• 2.Matrix FactorizationPTTFJAXMX
• 3.AutoRec: Rating Prediction with AutoencodersPTTFJAXMX
• 4.Personalized Ranking for Recommender SystemsPTTFJAXMX
• 5.Neural Collaborative Filtering for Personalized RankingPTTFJAXMX
• 6.Sequence-Aware Recommender SystemsPTTFJAXMX
• 7.Feature-Rich Recommender SystemsPTTFJAXMX
• 8.Factorization MachinesPTTFJAXMX
• 9.Deep Factorization MachinesPTTFJAXMX

Appendix: Mathematics for Deep Learning

• 1.Geometry and Linear Algebraic OperationsPTTFJAXMX
• 2.EigendecompositionsPTTFJAXMX
• 3.Single Variable CalculusPTTFJAXMX
• 4.Multivariable CalculusPTTFJAXMX
• 5.Integral CalculusPTTFJAXMX
• 6.Random VariablesPTTFJAXMX
• 7.Maximum LikelihoodPTTFJAXMX
• 8.DistributionsPTTFJAXMX
• 9.Naive BayesPTTFJAXMX
• 10.StatisticsPTTFJAXMX
• 11.Information TheoryPTTFJAXMX

Appendix: Tools for Deep Learning

• 1.Utility Functions and ClassesPTTFJAXMX