Modern Approaches to Behavioral Analysis

This is a Cajal NeuroKit course that combines online lectures about fundamentals and advanced neuroscience topics with hands-on and physical experiments.

Researchers from everywhere can participate because the course material is sent home in a kit box.

We will run a pre-course in May to train Teaching Assistants who would like to help us to teach this course locally or online. We will open applications soon.

Course overview

The goal of neuroscience is to understand how the nervous system controls behaviour [1], not only in the simplified environments of the lab, but also in the natural environments for which nervous systems evolved.

In pursuing this goal, neuroscience research is supported by an ever-larger toolbox, ranging from optogenetics to connectomics. However, often these tools are coupled with reductionist approaches for linking nervous systems and behaviour. Even though the arrival of deep learning tools for animal tracking has changed the scale at which behavioural data is acquired, the scope of questions that can be addressed with these tools can only be expanded when combined with a more nuanced and context-driven approach to the study of behaviour. This course will introduce advanced techniques for measuring and analysing behaviour, as well as three fundamental principles as necessary to understanding biological behaviour: (1) morphology and environment; (2) action-perception closed loops and purpose; and (3) individuality and historical contingencies [2].

[1] Preface, W.M. Cowan, Annual Review of Neuroscience 1978, Vol 1

[2] Gomez-Marin, A., & Ghazanfar, A. A. (2019). The life of behavior. Neuron, 104(1), 25-36

Course sponsor

What will you learn?

This course will emphasize the philosophical and observational skills required to understand behaviour, while also providing training in image-capture technologies and computer vision methods that can assist in the collection and analysis of video recorded behaviour datasets.

Focusing on the tool DeepLabCut, students will analyse an original video dataset and have the opportunity to practice tracking, pose estimation, action segmentation, kinematic analysis and modeling of behaviour.

By the end of the course, you will:

  • be familiar with modern and historical frameworks for studying the behaviour of living biological systems
  • practice methods for carefully and precisely observing and defining behaviours
  • understand the limits and capabilities of computer vision
  • develop an intuition for how to build experimental setups that can take advantage of tools such as DeepLabCut

This course shares and promotes open source software, and we encourage students to try new ideas, share insights, and connect with the open-source community.

Interested in teaching? We are hiring TAs!

We are looking for teaching assistants to help develop and deliver this course. TAs will be required to attend the pre-course at EPFL (September 19-23). They will then be paid an honorarium to teach the following courses. If you are interested, please fill out this form by [DEADLINE].


Alexander Mathis

Course Director EPFL, Switzerland

Danbee Kim

Course co- director Neurogears, UK

Keynote speakers

Nicola Clayton (Univ Cambridge, UK)

Ole Kiehn (Univ of Copenhagen, Denmark)

Guest Lecturers

Johanna T Schultz – (USC, Australia)

Nacho Sanguinetti (Harvard Univ. USA)


Day 1 – What is animal behaviour?

  • Historical and current theoretical frameworks for the study of behaviour in living biological systems

  • Practical exercises for training skills in observing and defining behaviours

Day 2 – Tools for modern-day ethology

  • Fundamentals of video recording, computer vision, and deep learning

  • Introduction to DeepLabCut

  • Create an original video recorded dataset of behaviour (students video record their animal puppet engaged in some kind of behaviour)

Day 3 – Training computers to see as we see

  • Multi-animal tracking

  • Live tracking

  • Prepare original video dataset of behaviour for analysis (students trade original video datasets and train their DLC networks)

Day 4 – Analysis by eye and by computer

  • Movement kinematics in living biological systems

  • Action segmentation – when does a behaviour start and end?

  • Analyse original video dataset of behaviour (students try to figure out what behaviour is being performed by their fellow students)

Day 5 – From individuals to populations

  • How do behaviours of living biological systems generalize?

  • Advanced DLC topics and typical pitfalls

  • Students pool all animal puppet videos and try to train DLC to categorize different behaviours

The course will be held from 14:00 to 18:00 GMT.


Registration fee: 500€ per person (includes shipping of the course kit, pre-recorded and live lectures before and during the course, full attendance to the course, and course certificate).

Registration fee for a group: 500€ for one person and one course kit + 150€ per additional person (without the course kit). For this course, groups can be up to 3 persons maximum sharing  1 single kit.

Applications for Teaching Assistants will open in May 2022

To receive more information about this NeuroKit, email

Subscribe to our newsletter

Keep up with our courses program and never miss an application date.