Assessing Animal Behavior

Description: A short introduction into cutting-edge methods for assessing animal behavior in a multi-modal and high-throughput fashion and deciphering animal behavior and neuronal activity in latent space.

Next course time: /
Venue: /

duration: 1.5 h (lecture, including a visit to our animal behavior facility) + 3 h (hands-on practical)
course held in: 2025, 2024, 2023
published: June 29, 2023
latest update: July 12, 2025 (12:08 pm)

Jump to Syllabus

Current announcements

Nothing at the moment.

Syllabus

Chapter 1: Behavioral experiments and animal welfare

Chapter 2: Multi-modal and high-throughput behavioral phenotyping

Chapter 3: Assessing animal behavior with machine learning

Chapter 4: Deciphering animal behavior and neuronal activity in latent space (incl. discussion)

Chapter 5: Hands-on: DeepLabCut

Learning outcomes

After completing this lecture series, students will be able to:

  • Explain the scientific importance of animal behavior experiments in neuroscience, including how behavioral studies contribute to understanding brain function, neural circuits, and the pathophysiology of neurological disorders.
  • Summarize the ethical guidelines governing animal research, with emphasis on the Three Rs principle (Replacement, Reduction, Refinement), and discuss national and EU-level regulations for animal welfare in neuroscience.
  • Identify and differentiate common animal models (e.g., mice, zebrafish, fruit flies) used in behavioral neuroscience, and discuss their specific advantages and limitations.
  • Describe multi-modal and high-throughput behavioral phenotyping approaches, including the integration of multiple sensors and recording modalities for comprehensive behavioral analysis.
  • Discuss and evaluate automated tracking systems and machine vision approaches for behavioral analysis, including their ability to increase data throughput, reduce bias, and improve reproducibility.
  • Explain the application of machine learning (ML) methods in behavioral data analysis, including supervised, unsupervised, and reinforcement learning, and their roles in automated classification and detection of behavioral patterns.
  • Apply knowledge of ML-based tools, such as DeepLabCut and VAME, for markerless pose estimation, behavior segmentation, and automated analysis of complex behavioral datasets.
  • Describe the challenges and strategies for analyzing high-dimensional behavioral and neural data, including the use of dimensionality reduction techniques (e.g., PCA, t-SNE, autoencoders, CEBRA) and their interpretational limitations.
  • Perform hands-on behavioral data analysis, including:
    • Installing and configuring DeepLabCut
    • Creating and managing new projects
    • Extracting and labeling video frames
    • Training and evaluating neural networks for pose estimation
    • Analyzing videos and interpreting results.
  • Critically assess the strengths, limitations, and ethical implications of modern behavioral phenotyping and analysis approaches, particularly regarding animal welfare and scientific reproducibility.

Acknowledgements

In order to keep the lecture material open and free, the use of copyright-protected material has been avoided. Instead, freely accessible YouTube movies are embedded and quoted. The organizer of this lecture is not the author of these videos and is not responsible for their content. The organizer uses the embedded sources according to fair principles for educational purpose.

The organizer of this lecture is not affiliated with the authors of the content in the provided external links, and bears no responsibility for their content. These links are used solely for educational purposes.

Past courses

  • Neuronal Circuit Dysfunction of C­NS diseases (WPM31), July 7, 2025
  • Neuronal Circuit Dysfunction of C­NS diseases (WPM31), June 24, 2024
  • Neuronal Circuit Dysfunction of C­NS diseases (WPM31), July 5, 2023



This course material is under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License (CC BY-NC-SA 4.0).

comments