Introduction to Machine Learning for the Sciences

TL;DR

This paper provides an introductory overview of machine learning techniques tailored for STEM students, covering fundamental methods, neural networks, interpretability, and reinforcement learning to facilitate their application in scientific projects.

Contribution

It offers a comprehensive beginner-friendly guide to machine learning concepts, including both classical and neural network approaches, with insights into interpretability and reinforcement learning.

Findings

Introduces key machine learning methods relevant to sciences

Explains neural network architectures and interpretability issues

Provides foundational knowledge for applying ML in scientific research

Abstract

This is an introductory machine-learning course specifically developed with STEM students in mind. Our goal is to provide the interested reader with the basics to employ machine learning in their own projects and to familiarize themself with the terminology as a foundation for further reading of the relevant literature. In these lecture notes, we discuss supervised, unsupervised, and reinforcement learning. The notes start with an exposition of machine learning methods without neural networks, such as principle component analysis, t-SNE, clustering, as well as linear regression and linear classifiers. We continue with an introduction to both basic and advanced neural-network structures such as dense feed-forward and conventional neural networks, recurrent neural networks, restricted Boltzmann machines, (variational) autoencoders, generative adversarial networks. Questions of interpretability are discussed for latent-space representations and using the examples of dreaming and adversarial attacks. The final section is dedicated to reinforcement learning, where we introduce basic notions of value functions and policy learning.