- A python file containing implementation of neural network from scratch
- A Jupyter Notebook demonstrating how to use the class
Our model uses a number of open source projects to work properly:
- Numpy - The fundamental package for scientific computing with Python
- Pandas - Python library for data manipulation
- Scikit - Simple and efficient tools for predictive data analysis
- Python-Programming language
Here we have implemented binary classification(on breast cancer dataset as an example) if required you can tweak the architecture. There are three activations implemented relu,tanh and sigmoid if require you can add more. You will have to input activations and the number of hidden units of each layer in a list to train the model
MIT Copyright <2021>