Skip to main content
grasp.study
About
Explore
Pricing
Log in
Try it for free
Back to course
👋
Welcome to a Grasp lesson
Create a free account
to keep studying and create your own study path.
ML_Supervised
·
Module 2
Optimization with Gradient Descent
Loss Functions and Parameters in Optimization
Explain the role of a loss function and a model's parameters in optimization.
2
NumPy Gradient Calculation for Multivariable Functions
Implement gradient calculation for simple multivariable functions using NumPy.
3
Batch Gradient Descent for Function Minimization
Implement batch gradient descent to find the minimum of a simple function.
4
SGD vs. Batch Gradient Descent: Convergence Comparison
Implement stochastic gradient descent (SGD) and compare its convergence behavior to batch gradient descent.
5
Mini-Batch Gradient Descent Implementation
Implement mini-batch gradient descent with a configurable batch size.
6
Learning Rate Scheduling for Optimization
Implement a simple learning rate scheduler (e.g., time-based decay) and apply it to an optimizer.
Previous module
Foundations of Supervised Learning and Evaluation
Next module
Linear Regression from Scratch