This page lists all tutorials available for the Shark machine learning library. The tutorials are ordered by the library modules they belong to. They cover only a tiny part of the library, but together with the more than 60 example programs they serve as starting points for learning how to develop machine learning software using Shark.
Using the Shark Library
- Simple Makefiles: This tutorial presents simple makefiles that can be used to start using the Shark library in your own projects.
- Using Arrays: This tutorial introduces the very basic features of the Array data structure and exception handling.
- Using Random Number Generators in Shark: This tutorial introduces the use of random number generators provided by Shark.
- Matrix Inversion: Matrix inversion is an important prerequisite for many algorithms. This tutorial shows how invert a matrix with Shark.
- Vectors and Matrices This tutorial introduces the classes Vector and Matrix which provide an object oriented interface to the LinAlg module.
- The EALib: This tutorial explains the basic data structures and concepts of the EALib.
- Travelling Salesman Problem: The tutorial introduces the well known traveling salesman problem and shows how the optimal solution to this problem can be approximated with a simple genetic algorithm (GA). This example reproduces a classical experiment and does not reflect the state-of-the-art in evolutionary algorithms for TSP.
- The (1+1)-CMA Evolution Strategy: This short tutorial shows how to do continous optimization using the (1+1)-CMA Evolution Startegy.
- Software Architecture: This tutorial explaines the ReClaM's software architecture and demonstrates its benefits.
- Linear Discriminant Analysis (LDA): The Linear Discriminant Analysis method is used to solve a multi-class classification problem.
- Feed-forward Neural Network I: This tutorial shows how to train a standard feed-forward multi-layer perceptron network to solve the XOR problem.
- Feed-forward Neural Network II: This mini-tutorial deals with advanced techniques for neural network training.
- Support Vector Machines: This tutorial teaches how to train and use a Support Vector Machine (SVM). The example demonstrates the binary classification SVM on toy data.
- Approximation of SVMs: In this tutorial you can learn how to reduce the number of support vectors used by an SVM model after training.
- Handling Configuration Files: This tutorial demonstrates how Shark supports the use of configuration files.