When people discuss AI, they often revolve around deep learning and neural networks. However, not all challenges require a GPU and 50 GB of training data. Sometimes, nature already has the answer.

In this session, we will explore Genetic Algorithms (GAs), an evolutionary approach to solving optimization and search problems implemented entirely in C# and .NET. You will learn how these algorithms mimic natural selection to evolve increasingly effective solutions over time.

We will construct a GA engine from scratch, examine encoding problems such as the traveling salesman or scheduling, and demonstrate how mutation, crossover, and fitness functions operate in practice. Throughout the session, we will highlight when GAs are appropriate, how to optimize their performance, and where they can complement or outperform other AI approaches.

Whether you are an AI enthusiast, a .NET developer interested in evolutionary computing, or simply someone who enjoys solving puzzles with code, this talk will introduce you to a powerful yet underutilized technique.

Who Should Attend:
• C# and .NET developers interested in alternative AI techniques
• Engineers solving optimization, search, or scheduling problems
• Developers looking for approachable, lightweight machine learning methods
• Anyone tired of black-box models and interested in transparent algorithmic logic

Key Takeaways:
• Understand the core concepts of Genetic Algorithms: population, fitness, selection, crossover, mutation
• Learn how to implement a working GA engine in C# and .NET
• Explore real-world applications like pathfinding, tuning algorithms, and adaptive behaviors
• Compare GAs to traditional AI/ML methods when to use which
• Get inspiration and resources to build your own evolutionary experiments