Skip to content

Using scikit-learn library created a handwritten digit recognizer algorithm working on MNIST dataset with f1-score of approximately 0.89.

Notifications You must be signed in to change notification settings

kondapalli19/-Hand-written-digit-2-recognition-in-MNIST-dataset

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 

Repository files navigation

Hand-written digit 2 recognition in MNIST dataset

Applying Logistic Regression

Build Status

Hand-written digit 2 recognition is a supervised machine learning model which is employ to recognize the digit 2 written in mnist dataset and gives the result as true/false. It gives a plot curve which shows the precision-recall of this model.

✨ MACHINE LEARNING MODEL WHICH VERIFIES THE DIGITS IN MNIST DATASET ✨

Features

  • Random number is given to the model
  • Recognizes the digits based on its learning and provides the result
  • If the digit is 2 it returns true otherwise false.

This model takes random digit of mnist dataset provided and produces the result on boolean datatype. As MNIST dataset writes on the Wikipedia

The MNIST database (Modified National Institute of Standards and Technology database) is a large database of handwritten digits that is commonly used for training various image processing systems The database is also widely used for training and testing in the field of machine learning.

Tech

Hand-written digit 2 recognition model uses a number of libraries to work properly:

Development

Want to contribute? Great! This can be further improvised using [SGD classifier]. Feel free to do a pull request it's free of cost and I'll be happy to merge your effective part.

License

Free Software, Hell Yeah!

Conclusion

Using scikit-learn library created a handwritten digit recognizer algorithm working on MNIST dataset with f1-score of approximately 0.89.

About

Using scikit-learn library created a handwritten digit recognizer algorithm working on MNIST dataset with f1-score of approximately 0.89.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published