ML/AI Algorithms from scratch in Python (numpy)

My practice playground for implementing the algorithms I come across while studying ML/AI.

Logistic Regression

LogisticRegression.py Binary classification (1 layer) model which predicts probability if a sample belongs to a given class or not. Hyperparametrs used:

• eta: Learning rate
• epochs: Number of iterations of learning
• random_state: Seed for random generator

Cost/Loss function: Log-likelihood

Optimizer: Batch gradient descent

linear_models:

Consists of codes for LinearRegression, LogisticRegression, Adaline, Perceptron

LeNet 5 Architecture (CNN)

• Implemented Forward propogation
• User can specify model hyperparameters like: Number of layers, number of nodes, type of layer(dense/conv/pool), learning rate, etc. --- Still in progress ---