🤓 Yashwanth's Notes

        • 1. Understanding Large Language Models
        • 2. Working with Text Data
        • 3. Coding Attention Mechanisms
        • 4. Implementing a GPT Model From Scratch to Generate Text
        • 5. Pretraining on Unlabeled Data
      • DDPM from Scratch
        • Inner Products
        • Lengths and Angles of Vectors
        • Matrix Representations of inner products
        • Norms
      • Autocorrelation
      • Hessian Matrix
      • Quasi-Newton Methods
      • Radial Basis Functions (RBFs)
      • Structural risk minimization
      • Symmetric Positive Definite Matrices (SPD Matrices)
      • The Conjugate Gradient Method
      • AlexNet - ImageNet Classification with Deep Convolutional Neural Networks
      • Identity Mappings in Deep Residual Networks
      • Keeping Neural Networks Simple by Minimizing the Description Length of the Weights
      • LeNet - Gradient-Based Learning Applied to Document Recognition
      • ResNet - Deep Residual Learning for Image Recognition
    Home

    ❯

    From Scratch

    Folder: From-Scratch

    2 items under this folder.

    • Feb 03, 2025

      DDPM from Scratch

      • Dec 16, 2024

        LLM-from-Scratch

        • folder

            • 1. Understanding Large Language Models
            • 2. Working with Text Data
            • 3. Coding Attention Mechanisms
            • 4. Implementing a GPT Model From Scratch to Generate Text
            • 5. Pretraining on Unlabeled Data
          • DDPM from Scratch
            • Inner Products
            • Lengths and Angles of Vectors
            • Matrix Representations of inner products
            • Norms
          • Autocorrelation
          • Hessian Matrix
          • Quasi-Newton Methods
          • Radial Basis Functions (RBFs)
          • Structural risk minimization
          • Symmetric Positive Definite Matrices (SPD Matrices)
          • The Conjugate Gradient Method
          • AlexNet - ImageNet Classification with Deep Convolutional Neural Networks
          • Identity Mappings in Deep Residual Networks
          • Keeping Neural Networks Simple by Minimizing the Description Length of the Weights
          • LeNet - Gradient-Based Learning Applied to Document Recognition
          • ResNet - Deep Residual Learning for Image Recognition

        Backlinks

        • No backlinks found

        Yashwanth's Notes

        • LinkedIn