LS100: Computational Behavioral Sciences
Foundations of Data Science and Applied AI/ML for Conducting Research in Behavioral Sciences
Learn to quantify the behavior of humans and other animals — movement, vocalizations, and digital traces — using Python, computer vision, audio analysis, and statistics. From your first line of code to a finished research project.
Start Here → · How to run the notebooks · View on GitHub
The course at a glance¶
6 modules · ~27 notebooks · 7 reading guides · 3 ways to run every notebook · from zero Python to deep learning and statistics
What is this course?¶
LS100 is a 4-credit, research-based course taught at Harvard University. It teaches you to conduct research that requires quantifying behavior, using automation, data science, and AI/ML methods. The materials are self-sufficient: they guide you from identifying a research question, to framing testable hypotheses, to using Python to collect, process, and analyze data, to communicating your findings.
What you’ll learn¶
By the end you will be able to:
Formulate behavior-related questions as testable scientific hypotheses.
Collect and process video, audio, and other digital data.
Use and fine-tune open-source AI/ML models (pose estimation, object tracking, audio embeddings) to extract behavioral metrics.
Apply statistical analyses to validate results.
Train classical ML models (supervised and unsupervised) to predict on new data.
Communicate findings through visualizations, talks, and written reports.
Use large language models responsibly in research workflows.
No prior programming experience required — Module 00B starts from zero.
Explore the modules¶
Turn an interest into a researchable question.
From variables to object-oriented design, for research.
Video → pose → kinematics → behavior classification.
Digital sound → features → clustering.
Choose and run the right statistical test.
Turn results into a clear scientific story.
How to run the notebooks¶
Every notebook can be run three ways — see How to run for details.
Best if you want to work offline on your own machine.
Best for a zero-install browser session with a free GPU.
Best for a full, pre-configured dev environment in the cloud.
Who this is for¶
Students enrolled in LS100, and anyone using computation to make sense of behavior.
Learners seeking a data-backed understanding of human or animal movement, vocalization, or behavioral data from sources like health portals and web services.
Instructors seeking non-commercial teaching resources in computational ethology and behavioral data science.
Licensed CC BY-NC 4.0 · How to cite · GitHub · LS100 — Computational Behavioral Sciences, Harvard University