Eriva Labs Logo
Eriva LabsBeta
HomePricing
LibrarySimulations
  1. Library
  2. AI Foundations: From Math to Neural Networks
  3. The Backward Pass
  4. Partial Derivatives and Gradients
Topic Overview

Partial Derivatives and Gradients

Isolate causal parameter effects in multivariable systems, calculate weight partial derivatives, and assemble gradient vectors for error descent.

Lessons in this Topic

1

Multivariable Systems and Freezing

Isolate causal parameter effects in multivariable systems, calculate weight partial derivatives, and assemble gradient vectors for error descent.

2

Calculating Partial Derivatives of Weights

Compute partial derivatives for individual parameter weights under Mean Squared Error loss by treating all competing weights as static constants.

3

Assembling the Multivariable Gradient Vector

Assemble individual partial derivatives into a unified gradient vector matching the exact dimensionality of the neural network parameter space.

4

Direction of Steepest Ascent and Descent

Analyze the geometric orientation of gradient vectors to establish why the negative gradient points along the path of steepest error reduction.

5

Partial Derivatives & Gradient Vectors In Practice

Master multivariable parameter isolation, partial derivative calculations, gradient vector assembly, and steepest descent trajectories through manual calculations.

Eriva Labs Logo
Eriva Labs

Mathematically rigorous. Intuitive by design. Step inside the concepts with visual diagrams, active simulations, and interactive laboratories.

Support

  • Simulations
  • About Us
  • Pricing
  • Contact Us

Legal

  • Terms of Service
  • Privacy Policy
  • Refund Policy

Policies

  • Cookie Policy
  • Acceptable Use

© 2026 Eriva Labs. All rights reserved.