Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision | |||
| deeplearningfoundationsandconcepts [2025/05/05 11:26] – gedbadmin | deeplearningfoundationsandconcepts [2025/05/05 11:30] (current) – gedbadmin | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| ====== Table of Contents ====== | ====== Table of Contents ====== | ||
| - | - [[>OneDeepLearningRevolution|The Deep Learning Revolution]] | + | - [[~:OneDeepLearningRevolution|The Deep Learning Revolution]] |
| - The Impact of Deep Learning | - The Impact of Deep Learning | ||
| - A Tutorial Example | - A Tutorial Example | ||
| - A Brief History of Machine Learning | - A Brief History of Machine Learning | ||
| - | - [[>TwoProbabilities|Probabilities]] | + | - [[~:TwoProbabilities|Probabilities]] |
| - The Rules of Probability | - The Rules of Probability | ||
| - Probability Densities | - Probability Densities | ||
| Line 12: | Line 12: | ||
| - Information Theory | - Information Theory | ||
| - Bayesian Probabilities | - Bayesian Probabilities | ||
| - | - [[>ThreStandardDistributions|Standard Distributions]] | + | - [[~:ThreStandardDistributions|Standard Distributions]] |
| - Discrete Variables | - Discrete Variables | ||
| - The Multivariate Gaussian | - The Multivariate Gaussian | ||
| Line 21: | Line 21: | ||
| - Kernel densities | - Kernel densities | ||
| - Nearest-neighbours | - Nearest-neighbours | ||
| - | - [[>FourSingleLayerNetworksRegression|Single Layer Networks: Regression]] | + | - [[~:FourSingleLayerNetworksRegression|Single Layer Networks: Regression]] |
| - Linear Regression | - Linear Regression | ||
| - Decision Theory | - Decision Theory | ||
| - The Bias-Variance Trade-off | - The Bias-Variance Trade-off | ||
| - | - [[>FiveSingleLayerNetworksClassification|Single-layer Networks: Classification]] | + | - [[~:FiveSingleLayerNetworksClassification|Single-layer Networks: Classification]] |
| - Discrimination Functions | - Discrimination Functions | ||
| - Decision Theory | - Decision Theory | ||
| - Generative Classifiers | - Generative Classifiers | ||
| - Discriminative Classifiers | - Discriminative Classifiers | ||
| - | - [[>SixDeepNeuralNetworks|Deep | + | - [[~:SixDeepNeuralNetworks|Deep |
| - Limitations of Fixed Basis Functions | - Limitations of Fixed Basis Functions | ||
| - Mulilayer Networks | - Mulilayer Networks | ||
| Line 36: | Line 36: | ||
| - Error Functions | - Error Functions | ||
| - Mixture Density Networks | - Mixture Density Networks | ||
| - | - [[>SevenGradientDescent|Gradient Descent]] | + | - [[~:SevenGradientDescent|Gradient Descent]] |
| - Error Surfaces | - Error Surfaces | ||
| - Gradient Descent Optimization | - Gradient Descent Optimization | ||
| Line 43: | Line 43: | ||
| - Batch Normalization | - Batch Normalization | ||
| - Layer Normalization | - Layer Normalization | ||
| - | - [[>EightBackpropegation|Backpropegations]] | + | - [[~:EightBackpropegation|Backpropegations]] |
| - Evaluation of Gradients | - Evaluation of Gradients | ||
| - Automatic Differntiation | - Automatic Differntiation | ||
| - | - [[>NineRegularization]] | + | - [[~:NineRegularization]] |
| - Induction Bias | - Induction Bias | ||
| - Weight Decay | - Weight Decay | ||
| Line 53: | Line 53: | ||
| - Residual Connections | - Residual Connections | ||
| - Model Averaging | - Model Averaging | ||
| - | - [[>TenConvolutionalNetworks|Convolutional | + | - [[~:TenConvolutionalNetworks|Convolutional |
| - Computer Vision | - Computer Vision | ||
| - Convulutional Filters | - Convulutional Filters | ||
| - General Graph Networks | - General Graph Networks | ||
| - | - [[> | + | - [[>~:EleventStructuredDistributions|Structured Distributions]] |
| - Graphical Models | - Graphical Models | ||
| - Conditional Independence | - Conditional Independence | ||
| - Sequence Models | - Sequence Models | ||
| - | - [[>TwelveTransforms|Transformers]] | + | - [[~:TwelveTransforms|Transformers]] |
| - Attention | - Attention | ||
| - Natural Language | - Natural Language | ||
| - Transformer Language Models | - Transformer Language Models | ||
| - Multimodal Transformers]] | - Multimodal Transformers]] | ||
| - | - [[>ThirteenGraphNeuralNetworks|Graph Neural Networks]] | + | - [[~:ThirteenGraphNeuralNetworks|Graph Neural Networks]] |
| - Machine Learning on Graphs | - Machine Learning on Graphs | ||
| - Neural Message-Passing | - Neural Message-Passing | ||
| - General Graph Networks | - General Graph Networks | ||
| - | - [[>FourteenSampling|Sampling]] | + | - [[~:FourteenSampling|Sampling]] |
| - Basic Sampling Algorithms | - Basic Sampling Algorithms | ||
| - Markov Chgain Monte Carlo | - Markov Chgain Monte Carlo | ||
| - Langevin Sampling | - Langevin Sampling | ||
| - | - [[>FifteenLatentVariables]] | + | - [[~:FifteenLatentVariables]] |
| - k-means Clustering | - k-means Clustering | ||
| - Mixture of Gaussians | - Mixture of Gaussians | ||
| - Expectation-Maximizastion Algorithm | - Expectation-Maximizastion Algorithm | ||
| - Evidence Lower Bound | - Evidence Lower Bound | ||
| - | - [[>SixteenContinuousLatentVariables|Continuous Latent Variables]] | + | - [[~:SixteenContinuousLatentVariables|Continuous Latent Variables]] |
| - Principal Component Analysis | - Principal Component Analysis | ||
| - Probabilistic Latent Variables | - Probabilistic Latent Variables | ||
| - Evidence Lower Bound | - Evidence Lower Bound | ||
| - Nonlinear Latent Variable Models | - Nonlinear Latent Variable Models | ||
| - | - [[>SeventeenGenerativeAdversarialNetworks|Generative Adversarial Networks]] | + | - [[~:SeventeenGenerativeAdversarialNetworks|Generative Adversarial Networks]] |
| - Adversarial Training | - Adversarial Training | ||
| - Image GANs | - Image GANs | ||
| - | - [[>EighteenNormalizingFlows|Normalizing Flows]] | + | - [[~:EighteenNormalizingFlows|Normalizing Flows]] |
| - Coupling Flows | - Coupling Flows | ||
| - Autoregressive Flows | - Autoregressive Flows | ||
| - Continuous Flows | - Continuous Flows | ||
| - | - [[>NineteenAutoencoders|Autoencoders]] | + | - [[~:NineteenAutoencoders|Autoencoders]] |
| - Deterministic Autoencoders | - Deterministic Autoencoders | ||
| - Variational Autoencoders | - Variational Autoencoders | ||
| - | - [[>TwentyDiffusionModels|Diffusion Models]] | + | - [[~:TwentyDiffusionModels|Diffusion Models]] |
| - Forward Encoder | - Forward Encoder | ||
| - Reverse Encoder | - Reverse Encoder | ||
| Line 101: | Line 101: | ||
| * Appendices | * Appendices | ||
| - | - [[>A1LinearAlgebra|Linear Algebra]] | + | - [[~:A1LinearAlgebra|Linear Algebra]] |
| - | - [[>A2CalculusOfVariations|Calculus of Variations]] | + | - [[~:A2CalculusOfVariations|Calculus of Variations]] |
| - | - [[>A3LagrangeMultipliers|Lagrange Multipliers]] | + | - [[~:A3LagrangeMultipliers|Lagrange Multipliers]] |