Deep Learning
Browse all articles with this tag
Deep Learning Notes - 3: Classification Models and Introduction to Deep Neural Networks
Deep Learning Notes - 3, covering classification models (discriminant functions, logistic regression, softmax) and deep neural networks (activation functions, transfer learning, mixture density networks). Corresponding to Chapters 5-6 of "Deep Learning: Fundamentals and Concepts".
Deep Learning Notes - 4: Gradient Descent, Backpropagation, and Regularization
Deep Learning Notes - 4, covering gradient descent, backpropagation, and regularization. Corresponding to Chapters 7-9 of "Deep Learning: Foundations and Concepts".
Deep Learning Notes - 5: Convolutional Networks and Probabilistic Graphical Models
Deep Learning Notes - 5, covering Convolutional Neural Networks (convolution, pooling, object detection, image segmentation, style transfer) and Probabilistic Graphical Models (Bayesian networks, conditional independence, d-separation). Corresponds to Chapters 10-11 of "Deep Learning: Fundamentals and Concepts".
Deep Learning Notes - 7: Sampling Methods and Latent Variable Models
Deep Learning Notes - 7, covering sampling methods (Monte Carlo, MCMC, Gibbs sampling), discrete latent variables (K-means, GMM, EM algorithm), and continuous latent variables (PCA, probabilistic PCA). Corresponding to Chapters 14-16 of "Deep Learning: Fundamentals and Concepts".
Deep Learning Notes - 8: GANs, Normalizing Flows, Autoencoders, and Diffusion Models
Deep Learning Notes - 8, covering four major generative models: GANs, normalizing flows, autoencoders and variational autoencoders (VAE), and diffusion models. Corresponds to Chapters 17-20 of "Deep Learning: Foundations and Concepts".
Deep Learning Notes-1: Polynomial Fitting, Probability Theory, and Information Theory Fundamentals
Deep Learning Notes-1, covering overfitting and underfitting, regularization, probability theory fundamentals (Bayes' theorem, Gaussian distribution, maximum likelihood estimation), and information theory (entropy and KL divergence). Corresponds to Chapters 1-2 of "Deep Learning: Foundations and Concepts".
Deep Learning Notes-2: Probability Distributions, Linear Regression, and the Bias-Variance Tradeoff
Deep Learning Notes-2, covering the Bernoulli distribution, multinomial distribution, multivariate Gaussian distribution, the probabilistic derivation of linear regression, decision theory, and the bias-variance tradeoff. Corresponds to Chapters 3-4 of "Deep Learning: Foundations and Concepts".
Deep Learning Notes-6: Transformer and Graph Neural Networks
Deep Learning Notes-6, covering the Transformer attention mechanism (self-attention, multi-head attention, positional encoding), language models (GPT/BERT), and graph neural networks (message passing, graph convolution, graph attention). Corresponds to Chapters 12-13 of "Deep Learning: Foundations and Concepts".