🤖🧠 Deep mind AI blog series

      • Agent evaluation
      • Agentic workflow
      • agentic-workflow-deep-dive
      • Basics
      • Integrating tools, functions with the ChatGPT
      • Memory
      • Meta prompting
      • Response caching and its role in agents
      • XOR NN
        • 1. Project Outline
        • 2. Training Data
        • 3. Data generation pipeline
        • 4. Neural network development
        • 5. Project investigate
        • 6. Hyperparameter Tuning Guide
        • 7. Evaluation
        • 8. Multi-Modal Neural Architecture
        • Distance-Based Perception System (Outdated)
        • QA
      • Organisation ID error
      • Plots are not visible after deploying to github
      • Activation function
      • Ai Human Brain Overlaps
      • An Introduction to Self-Supervised Learning, How Machines Teach Themselves
      • AND Vs XOR using NN
      • Back propagation Calculus
      • Cost function
      • Delta error
      • Epochs
      • Gradient descent
      • Heuristics in Programming, Navigating Complex Problems with Intelligent Shortcuts
      • Improving NN learning
      • Learning is slow for sigmoid
      • Learning Rate
      • Mathematics
      • Neural Network Learning Polynomial
      • NN Learning
      • Overfitting
      • Vanishing gradient problem
      • Weights and Biases
      • What is convolution
      • What is Tensor
      • Assistant API
      • Assistant vs Chat completion api
      • ChatGPT outputs
      • Model Context Protocol (MCP)
      • Ollama
      • Prompt Engineering
      • Pydantic model and Json Schema for structured output
      • Text to speech
      • Tokens and latency
      • LLM in robotics
      • Open challenges and long term road map in Robotics
      • Simulation for robotics
      • Vision Action Model VAL
      • AI Podcast
      • Emergent Properties of Large Language Models
      • Empirical Study Feature Engineering vs Hyperparameter Tuning in Robot Navigation
      • Getting started with deep learning study guide
      • How Large Language Models Learn the Theory of Mind
      • Web socket
      • Why Better Data Beats Better Models — A First Principles View
    Home

    ❯

    First Principles

    ❯

    Gradient descent

    Gradient descent

    Oct 06, 20251 min read

    Learning Rate Back propagation calculus NN Learning

    Gradient descent Vs Mini batch Stochastic Gradient descent Randomly shuffle your training data and divide it into a bunch of mini-batches Why are there different optimizers?


    Graph View

    Backlinks

    • Delta error
    • Learning Rate

    Created with Quartz v4.4.0 © 2025

    • GitHub
    • Discord Community