ymanzi / multilayer-perceptron

Implement a multilayer perceptron from scratch, in order to predict whether a cancer is malignant or benign on a dataset of breast cancer diagnosis in the Wisconsin.

Multilayer Perceptron

Subject: Multilayer Perceptron 42

Member: 🌜 Ymanzi 🌛

More Explanations: NeuralNetwork Lib

Challenge

Implement a multilayer perceptron from scratch, in order to predict whether a cancer is malignant or benign on a dataset of breast cancer diagnosis in the Wisconsin.

How to Use It

➣ Make train

Will train the model with the dataset python3.8 train.py DATASET_NAME.csv

➣ Make predict

Will make a prediction based on the train network and the dataset python3.8 predict.py NN_FILE.pickle DATASET_NAME.csv

Resources

• Activation Functions
• Neural Network Tutorial
• Sigmoid Activation
• Weight initialization
• He Initialization
• Dropout Regularization
• Dropout vs Dropout Connect
• Momentum Intuitive Explanation