MLKit

What is MLKit?

MLKit is a simple machine learning framework written in Swift. Currently MLKit features machine learning algorithms that deal with the topic of regression, but the framework will expand over time with topics such as classification, clustering, recommender systems, and deep learning. The vision and goal of this framework is to provide developers with a toolkit to create products that can learn from data. MLKit is a side project of mine in order to make it easier for developers to implement machine learning algorithms on the go, and to familiarlize myself with machine learning concepts.

Features: 

• Matrix and Vector Operations (uses Upsurge framework)
•  Simple Linear Regression (Allows for 1 feature set)
•  Polynomial Regression (Allows for multiple features)
•  Ridge Regression
•  Multi-Layer Feed Forward Neural Network
•  K-Means Clustering
•  Genetic Algorithms
•  Allows for splitting your data into training, validation, and test sets.
•  K-Fold Cross Validation & Ability to test various L2 penalties for Ridge Regression
•  Single Layer Perceptron, Multi-Layer Perceptron, & Adaline ANN Architectures

Overview