/artificial-neural-network

An implementation of artificial neural networks using only numpy and python functions.

Primary LanguageJupyter Notebook

Artificial Neural Networks | Support Vector Machines | Synthetic Minority Oversampling Technique

A simple implementation of artificial neural networks using numpy as randomizers and python function only. This could still be improved by using faster functions in Numpy. Additionally, Synthethic Minority Oversampling Technique (SMOTE) was also used to handle class imbalance.

Data Availability

Data used was removed but a report is provided for visual appreciation.

Performance of varying polynomial degrees

alt text

Dependencies

  • numpy
  • collections
  • matplotlib
  • imblearn
  • timeit
  • sklearn