Syllabus¶

Title: Tracking Animal Behavior - Block Seminar
ID: 118924
Credits: 3
Workload: 2 semester hours per week
Semester: WS 21/22 Ruhr-University Bochum
Lecturer: Guillermo Hidalgo Gadea

Description¶

New advances in computer vision and machine learning have changed the way we measure spatiotemporal dynamics of animal movement from video data. But do we really understand Animal Behavior? This hands-on seminar will introduce new advances in the field of computational neuroethology and teach you how to use animal tracking software such as DeepLabCut (Mathis et al., 2018) and BORIS (Friard et al., 2016) to analyze animal behavior. We will learn basic python skills for data analysis as well as state-of-the-art computer vision techniques to analyze video data. You will work on individual projects to gain practical experience and will end discussing the boundaries of what constitutes behavior. From mere location in space, to body pose, movement and goal-orientedness.

Expectations¶

Programming skills are not necessary, but technical affinity and basic computer skills will be advantageous. The course language may be either English or German, depending on students’ background. The Block seminar will consist of one introductory session and six seminar days, grouped in three consecutive blocks. The final schedule will be discussed on Friday, October 22nd, 2021. The course will consist of lectures, discussions, group improvs and hands on exercises. Group improvs are an active learning strategy consisting of short (unprepared) presentations of ongoing group projects. The seminar will not be graded, but active participation and classroom interaction is necessary to pass the class.

Contents¶

Note

The schedule content and duration may be subject to slight changes at short notice.

Introduction, Fr. 22.10.2021 2pm

Lecture: About me and Syllabus
Discussion: Scheduling
Lecture: Presentation of datasets
Discussion: Project assignment

Block 1, day 1

Lecture: What is behavior and what does it mean for psychologists?
Group improv: Project proposal, hypotheses, and operationalization
Lecture: How can we measure animal behavior?
Hands on: Installing and scoring in BORIS

Block 1, day 2

Discussion: Recap measuring behavior and BORIS
Lecture: Intro and how to use DeepLabCut
Hands on: Dummy DeepLabCut project
Group improv: Updated project proposal

Homework: Own data collection (if necessary)

Block 2, day 3

Discussion: Recap DeepLabCut workflow
Lecture: Recent advances in computational ethology
Group improv: Methods, and analysis
Hands on: DeepLabCut projects (data management)

Block 2, day 4

Discussion: DeepLabCut Troubleshooting
Hands on: DeepLabCut projects (labeling)

Individual appointments (if necessary)

Training DLC model with GPU
Analyzing videos with GPU

Block 3, day 5

Discussion: Recap DeepLabCut troubleshooting
Group improv: DeepLabCut results
Lecture: Introduction to data analysis
Hands on: Kinematic analysis and unsupervised ML in python (scripts provided)

Block 3, day 6

Hands on: Data analysis
Hands on: Prepare final presentation
Group improv: Hypothesis, methods, and results
Discussion: Pros and cons of DeepLabCut