Skip to content

Machine Learning Exercise Creating a Linear Classify with Gradient Descent from Scratch

Notifications You must be signed in to change notification settings

shaelm/Children-Height-CIFAR10-classfication

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Children-Height-CIFAR10-classfication

Machine Learning Exercise Creating a Linear Classify with Gradient Descent from Scratch. This was an excersise in my machine learning class to create a Linear Classifier from scratch writing functions for gradient descent , calculating loss, and training the weights. Used Numpy matrix math to minimize any looping within the program. Jupyter Notebooks are Attached.

Kid Height Data

Attached CSV with Child Height Data with two features as predictors.

CIFAR10 Data

Attached Train and Test Batches of CIFAR 10 Dataset. Learned 10-2 Class Classifiers to Predict the data. Although I realize this is not the most efficient or best way to do this, it was a good exercise to learn how to create a classifier, and program loss and gradient functions without using libaries.

Image Templates of 10 Learned Weight Vectors From Class 0-9 of CIFAR 10

Screenshot Screenshot Screenshot Screenshot Screenshot Screenshot Screenshot Screenshot Screenshot Screenshot

About

Machine Learning Exercise Creating a Linear Classify with Gradient Descent from Scratch

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published