Home Data Science Notes Contact

Deep Learning

  • Generative Deep Learning - 2nd Edition - David Foster
  • Book
  • 1. Introduction
  • 1.1. From neural networks to deep learning (handout)
  • 1.2. Current applications and success (handout)
  • 1.3. What is really happening? (handout)
  • 1.4. Tensor basics and linear regression (handout)
  • 1.5. High dimension tensors (handout)
  • 1.6. Tensor internals (handout)
  • 2. Machine Learning Fundamentals
  • 2.1. Loss and risk (handout)
  • 2.2. Over and under fitting (handout)
  • 2.3. Bias-variance dilemma (handout)
  • 2.4. Proper evaluation protocols (handout)
  • 2.5. Basic clusterings and embeddings (handout)
  • 3. Multi-layer Perceptron and Backpropagation
  • 3.1. The perceptron (handout)
  • 3.2. Probabilistic view of a linear classifier (handout)
  • 3.3. Linear separability and feature design (handout)
  • 3.4. Multi-Layer Perceptrons (handout)
  • 3.5. Gradient descent (handout)
  • 3.6. Back-propagation (handout)
  • 4. Graphs of operators, autograd, and convolutional layers
  • 4.1. DAG networks (handout)
  • 4.2. Autograd (handout)
  • 4.3. PyTorch modules and batch processing (handout)
  • 4.4. Convolutions (handout)
  • 4.5. Pooling (handout)
  • 4.6. Writing a PyTorch module (handout)
  • 5. Initialization and optimization
  • 5.1. Cross-entropy loss (handout)
  • 5.2. Stochastic gradient descent (handout)
  • 5.3. PyTorch optimizers (handout)
  • 5.4. L2 and L1 penalties (handout)
  • 5.5. Parameter initialization (handout)
  • 5.6. Architecture choice and training protocol (handout)
  • 5.7. Writing an autograd function (handout)
  • 6. Going deeper
  • 6.1. Benefits of depth (handout)
  • 6.2. Rectifiers (handout)
  • 6.3. Dropout (handout)
  • 6.4. Batch normalization (handout)
  • 6.5. Residual networks (handout)
  • 6.6. Using GPUs (handout)
  • 7. Autoencoders
  • 7.1. Transposed convolutions (handout)
  • 7.2. Deep Autoencoders (handout)
  • 7.3. Denoising autoencoders (handout)
  • 7.4. Variational autoencoders (handout)
  • 8. Computer vision
  • 8.1. Computer vision tasks (handout)
  • 8.2. Networks for image classification (handout)
  • 8.3. Networks for object detection (handout)
  • 8.4. Networks for semantic segmentation (handout)
  • 8.5. DataLoader and neuro-surgery (handout)
  • 9. Under the hood
  • 9.1. Looking at parameters. (handout)
  • 9.2. Looking at activations (handout)
  • 9.3. Visualizing the processing in the input (handout)
  • 9.4. Optimizing inputs (handout)
  • 10. Autoregression and Normalizing Flows
  • 10.1. Auto-regression (handout)
  • 10.2. Causal convolutions (handout)
  • 10.3. Non-volume preserving networks (handout)
  • 11. Generative Adversarial Networks
  • 11.1. Generative Adversarial Networks (handout)
  • 11.2. Wasserstein GAN (handout)
  • 11.3. Conditional GAN and image translation (handout)
  • 11.4. Model persistence and checkpoints (handout)
  • 12. Recurrent models and NLP
  • 12.1. Recurrent Neural Networks (handout)
  • 12.2. LSTM and GRU (handout)
  • 12.3. Word embeddings and translation (handout)
  • 13. Attention models
  • 13.1. Attention for Memory and Sequence Translation (handout)
  • 13.2. Attention Mechanisms (handout)
  • 13.3. Transformer Networks (handout)
  • Practice Questions
  • Practice 1 (Solution)
  • Practice 2 (Solution)
  • Practice 3 (Solution)
  • Practice 4 (Solution)
  • Practice 5 (Solution)
  • Practice 6 (Solution)
  • Book PDF
  • Notebooks
  • Chapter 1 - Introduction (pptx)
  • Chapter 2 - Supervised Learning (pptx)
  • Chapter 3 - Shallow Neural Networks (pptx)
  • Chapter 4 - Deep Neural Networks (pptx)
  • Chapter 5 - Loss Functions (pptx)
  • Chapter 6 - Training Models (pptx)
  • Chapter 7 - Gradients and Initializations (pptx)
  • Chapter 8 - Measuring Performance (pptx)
  • Chapter 9 - Regularization (pptx)
  • Chapter 10 - Convolutional Networks (pptx)
  • Chapter 11 - Residual Networks (pptx)
  • Chapter 12 - Transformers (pptx)
  • Chapter 13 - Graph Neural Networks (pptx)
  • Chapter 14 - Unsupervised Learning (pptx)
  • Chapter 15 - Generative Adversarial Networks (pptx)
  • Chapter 16 - Normalizing Flows (pptx)
  • Chapter 17 - Variational Autoencoders (pptx)
  • Chapter 18 - Diffusion Models (pptx)
  • Chapter 19 - Deep Reinforcement Learning (pptx)
  • Chapter 20 - Why does deep learning work? (pptx)
  • Chapter 21 - Deep Learning and Ethics (pptx)
  • Appendices (pptx)
  • Transformer Models
  • Using HF Transformers
  • Fine-tuning Pretrained Models
  • Sharing Models and Tokenizers
  • HF Datasets Library
  • HF Tokenizers Library
  • Main NLP Tasks
  • Building and Sharing Demos
  • Transformers by Brandon Rohrer
  • Transformers by Michael Phi
  • Transformers: Python Implementation
  • Transformers: Python Implementation (PDF)
  • Transformers Catalogue
  • Chapter 1
  • 1 - An Introduction to Deep Learning System Design
  • 2 - Dataset Management Service
  • 3 - Model Training Service
  • 4 - Distributed Training
  • 5 - Hyperparameter Optimization (HPO) Service
  • 6 - Model Serving Design
  • 7 - Model Serving in Practice
  • 8 - Metadata and Artifact Store
  • 9 - Workflow Orchestration
  • 10 - Path to Production
  • Appendix A: A Hello World Deep Learning System
  • Appendix B: Survey of Existing Solutions
  • Appendix C: Creating an HPO Service With Kubflow Katib
  • Chapter 1
  • Part 1 - Model Prompting
  • Part 2 - Use Case Ideation
  • Part 3 - The Generate Endpoint
  • Part 4 - Creating Custom Models
  • Part 5 - Chaining Prompts
  • 1 - Intro to LLMs and the generative AI project lifecycle
  • Lab 1
  • 2 - Fine-tuning and evaluating large language models
  • Lab 2
  • 3 - Reinforcement learning and LLM-powered applications
  • Lab 3
  • Vinija's AI Notes: LLM Models
  • Vinija's AI Notes: Prompt Engineering
  • 7 Frameworks for Serving LLMs
  • ToolLLM
  • COURSE: Building LLM-Powered Apps by Weights and Biases
  • Patterns for Building LLM-based Systems & Products
  • LLM-Rec: Personalized Recommendation via Prompting Large Language Models
  • GitHub Repo for LLM-Human Aligning
  • Llama 2 - Guidance and Best Practices for Building LLM Applications
  • Challenges and Applications of Large Language Models
  • What are GPT Agents? A deep dive into the AI interface of the future
  • Open Problems and Fundamental Limitations of RLHF
  • Llama 2: Open Foundation and Fine-Tuned Chat Models
  • MetaGPT
  • COURSE: Langchain & Vector Databases in Production by Activeloop
  • LlamaIndex
  • MLflow AI Gateway by Databricks
  • Understanding LLaMA-2 Architecture & its Ginormous Impact on GenAI
  • LLM Powered Autonomous Agents
  • AWS Guides on Generative AI
  • HELM (Holistic Evaluation of Language Models), HELM Docs
  • Comparison of LLMs
  • LangChain Academy - Introduction to LangGraph
  • DEEPLEARNING.AI - Automated Testing for LLMOps (AVAILABLE SOON)
  • DEEPLEARNING.AI - Prompt Engineering for Vision Models (AVAILABLE SOON)
  • DEEPLEARNING.AI - Quantization in Depth (AVAILABLE SOON)
  • DEEPLEARNING.AI - Quantization Fundamentals with HuggingFace (AVAILABLE SOON)
  • DEEPLEARNING.AI - Getting Started with Mistral (AVAILABLE SOON)
  • DEEPLEARNING.AI - Preprocessing Unstructured Data for LLM Applications (AVAILABLE SOON)
  • DEEPLEARNING.AI - Building and Evaluating Advanced RAG Applications (AVAILABLE SOON)
  • DEEPLEARNING.AI - Vector Databases: from Embeddings to Applications (AVAILABLE SOON)
  • DEEPLEARNING.AI - How Diffusion Models Work? (AVAILABLE SOON)
  • DEEPLEARNING.AI - Efficiently Serving LLMs (AVAILABLE SOON)
  • DEEPLEARNING.AI - Knowledge Graphs for RAG (AVAILABLE SOON)
  • DEEPLEARNING.AI - Advanced Retrieval for AI with Chroma (AVAILABLE SOON)
  • DEEPLEARNING.AI - Building Agentic RAG with LlamaIndex
  • DEEPLEARNING.AI - LLMs with Semantic Search (Cohere)
  • DEEPLEARNING.AI - LangChain
  • DEEPLEARNING.AI - Prompt Engineering
  • DEEPLEARNING.AI - Building Systems with the ChatGPT API
  • DEEPLEARNING.AI - LangChain: Chat With Your Data
  • DEEPLEARNING.AI - OpenAI Functions, Tools, and Agents in LangChain
  • DEEPLEARNING.AI - Multimodal Llama 3.2
  • Building LLM Applications for Production by Chip Huyen
  • Open challenges in LLM research by Chip Huyen
  • LLMOps by Vinija
  • Instruction Tuning for Large Language Models: A Survey
  • RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
  • A complete Hugging Face tutorial: how to build and train a vision transformer
  • How the Vision Transformer (ViT) works in 10 minutes: an image is worth 16x16 words
  • Transformers in computer vision: ViT architectures, tips, tricks and improvements
  • The theory behind Latent Variable Models: formulating a Variational Autoencoder
  • How diffusion models work: the math from scratch
  • GANs in computer vision - Introduction to generative learning
  • GANs in computer vision - Improved training with Wasserstein distance, game theory control and progressively growing schemes
  • How Graph Neural Networks (GNN) work: introduction to graph convolutions from scratch
  • Best Graph Neural Network architectures: GCN, GAT, MPNN and more
  • Explainable AI (XAI): A survey of recents methods, applications and frameworks
  • In-layer normalization techniques for training very deep neural networks
  • Why multi-head self attention works: math, intuitions and 10+1 hidden insights
  • How Positional Embeddings work in Self-Attention (code in Pytorch)
  • Grokking self-supervised (representation) learning: how it works in computer vision and why
  • How Attention works in Deep Learning: understanding the attention mechanism in sequence models
  • How Transformers work in deep learning and NLP: an intuitive introduction
  • Learn Pytorch: Training your first deep learning models step by step
  • A complete Apache Airflow tutorial: building data pipelines with Python
  • BYOL tutorial: self-supervised learning on CIFAR images with code in Pytorch
  • How Neural Radiance Fields (NeRF) and Instant Neural Graphics Primitives work
  • How distributed training works in Pytorch: distributed data-parallel and mixed-precision training
  • Vision Language models: towards multi-modal deep learning
  • Understanding Maximum Likelihood Estimation in Supervised Learning
  • Grokking self-supervised (representation) learning: how it works in computer vision and why
  • Speech Recognition: a review of the different deep learning approaches
  • A complete Weights and Biases tutorial
  • Regularization techniques for training deep neural networks
  • Top Resources to start with Computer Vision and Deep Learning
  • Tensorflow Extended (TFX) in action: build a production ready deep learning pipeline
  • An introduction to Recommendation Systems: an overview of machine and deep learning architectures
  • An overview of Unet architectures for semantic segmentation and biomedical image segmentation
  • How Graph Neural Networks (GNN) work: introduction to graph convolutions from scratch
  • Best Resources to Learn Deep Learning Theory
  • Build a Transformer in JAX from scratch: how to write and train your own models
  • JAX vs Tensorflow vs Pytorch: Building a Variational Autoencoder (VAE)
  • JAX for Machine Learning: how it works and why learn it
  • Understanding einsum for Deep learning: implement a transformer with multi-head self-attention from scratch
  • Introduction to medical image processing with Python: CT lung and vessel segmentation without labels
  • Best deep CNN architectures and their principles: from AlexNet to EfficientNet
  • How Transformers work in deep learning and NLP: an intuitive introduction
  • A journey into Optimization algorithms for Deep Neural Networks
  • Introduction to Kubernetes with Google Cloud: Deploy your Deep Learning model effortlessly
  • How to use Docker containers and Docker Compose for Deep Learning applications
  • Transfer learning in medical imaging: classification and segmentation
  • Scalability in Machine Learning: Grow your model to serve millions of users
  • How to use uWSGI and Nginx to serve a Deep Learning model
  • Deploy a Deep Learning model as a web application using Flask and Tensorflow
  • Distributed Deep Learning training: Model and Data Parallelism in Tensorflow
  • How to train a deep learning model in the cloud
  • How to build a custom production-ready Deep Learning Training loop in Tensorflow from scratch
  • Data preprocessing for deep learning: Tips and tricks to optimize your data pipeline using Tensorflow
  • Understanding coordinate systems and DICOM for deep learning medical image analysis
  • How to Unit Test Deep Learning: Tests in TensorFlow, mocking and test coverage
  • Understanding the receptive field of deep convolutional networks
  • Logging and Debugging in Machine Learning - How to use Python debugger and the logging module to find errors in your AI application
  • Best practices to write Deep Learning code: Project structure, OOP, Type checking and documentation
  • Intuitive Explanation of Skip Connections in Deep Learning
  • Deep learning in medical imaging - 3D medical image segmentation with PyTorch
  • Deep Learning Algorithms - The Complete Guide
  • Human Pose Estimation
  • Graph Neural Networks - An overview
  • Localization and Object Detection with Deep Learning
  • Trust Region and Proximal policy optimization (TRPO and PPO)
  • Semantic Segmentation in the era of Neural Networks
  • YOLO - You only look once (Single shot detectors)
  • Unravel Policy Gradients and REINFORCE
  • The idea behind Actor-Critics and how A2C and A3C improve them
  • Deep Q Learning and Deep Q Networks
  • The secrets behind Reinforcement Learning
  • Decrypt Generative Adversarial Networks (GAN)
  • Self-driving cars using Deep Learning
  • Predict Bitcoin price with Long sort term memory Networks (LSTM)
  • How to Generate Images using Autoencoders
  • Neural Network from scratch-part 1
  • Neural Network from scratch-part 2
  • Document clustering
  • Research Papers Highlights and Notes - Comprehensive List
  • ...