Machine learning algorithms in Go

Introduction

This project aims to provide minimalistic machine learning algorithms in Go. We will aspire to efficient implementation of these algorithms, and we will take advantage of Go's concurrency paradigm wherever possible.

Status

Clustering

Implemented

• Gaussian mixture model
• k-means, k-medians, k-medoids
• single-linkage hierarchical clustering

In-progress

• generic hierarchical clustering
• spectral clustering
• Hierarchical Ordered Partitioning and Collapsing Hybrid (HOPACH)

Planned

• self-organizing maps

Classification

Planned

• k-means based classifier
• feed-forward neural network
• support-vector machine
• naive Bayes

Modeling

Planned

• hidden Markov model