Machine Learning: The Bare Math Behind Libraries - Supervised Learning

by Łukasz Gebel, Piotr Czajka

AI/Machine Learning English
AI/Machine Learning

Machine learning one of the most innovative fields in computer science – yet people use libraries as black boxes. We will start by defining what machine learning is and equip you with an intuition of how it works. Then we'll explain gradient descent algorithm using linear regression and project it to supervised neural networks training. Within unsupervised learning (part 2), you will become familiar with Hebb’s learning and learning with concurrency. Our aim is to show the mathematical basics of neural networks for those who want to start using machine learning in their day-to-day work.

Łukasz Gebel
Senior Software Engineer, TomTom

Software engineer at TomTom by day, machine learning enthusiast at night. My leading technology is Java and Java-based frameworks. On a daily basis, I work on designing, implementing and deploying distributed systems that work in cloud environments, such as Microsoft Azure and AWS. I'm interested in classification problems and multi-agent systems. I love to learn, read books and play football – in no particular order.

Piotr Czajka
Expert Software Engineer, TomTom

Programmer, retired mage, bookworm, storyteller and liberal arts devotee.

I'm into language semantics, its understanding and impact on the way people think. I love both natural and programming languages - professionally my heart belongs to Java, but I cheat on her with Python, Scala and, occasionally, other beautiful languages. In addition to my work at TomTom as a software engineer a I'm keen on artificial intelligence, mainly for natural language understanding. If we are to reach technological singularity, we better get on it!