NEWVectors or files. Pick a path.Start →
    Back to Videos

    Gradient Descent Explained: How Models Actually Learn (and Where RAG Fits)

    95
    AI Concepts Explained
    Mixpeek Team
    July 19, 2026

    Summary

    Every trained model, from a two-parameter line to a trillion-parameter LLM, learns the same way: measure the error, follow the slope downhill, repeat. This visual walkthrough builds gradient descent from a loss landscape, shows learning rates and local minima, and connects it to information retrieval: ranking functions and rerankers are trained by the same descent on relevance labels and click signals.

    gradient-descentmachine-learning-basicsoptimizationtraininglearning-to-rank

    About this video

    Every trained model, from a two-parameter line to a trillion-parameter LLM, learns the same way: measure the error, follow the slope downhill, repeat. This visual walkthrough builds gradient descent from a loss landscape, shows learning rates and local minima, and connects it to information retrieval: ranking functions and rerankers are trained by the same descent on relevance labels and click signals.

    Frequently Asked Questions