Skip to content

gilpasternak35/ANN-from-scratch-python

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ANN-from-scratch-python

A one week hackathon project, mathed, whiteboarded, and derived entirely from scratch. Partner coded by @limpa105 and @gilpasternak35. Extensible design, best implementation practices and comprehensible test coverage.

Features include:

  • Cached Recursive backpropogation
  • Synthetic data testing
  • Intuitive API
  • Object oriented design
  • Comprehensive input validation.

All computations done across all training examples simultaneously.

Next steps:

  • Addition of batching
  • Dropout
  • Extension to an RNN

About

A from-scratch ANN implementation, without the use of Machine Learning libraries

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 82.0%
  • Jupyter Notebook 18.0%