The 2022 Short Course on the Application of Machine Learning for Automated Quantification of Behavior

The Jackson Laboratory

Oct 10-13, 2022

7:45 am - 8:30 pm EST

General Information

Over the past few years, behavior quantification and modeling has experienced an explosion of innovation and discovery largely enabled by application of new machine learning methods. These methods have enabled the quantification of behavior at high temporal and spatial resolution, and in concordance with simultaneous measurement and manipulation of neural and genetic function. However, access to this revolutionary technology is limited primarily due to a lack of adequate resources and training. Democratization of this technology through training of the next generation of scientists is necessary to elevate the field of quantitative behavior. The Short Course on the Application of Machine Learning for Automated Quantification of Behavior will disseminate the theoretical and technical knowledge of this field, and train researchers to apply machine learning methods to behavior quantitation and modeling. Our goal is to build an educational program that fosters productive and interactive dialogue, teaches proper methodology, and provides support structure to nurture and lower the barrier of entry into this nascent field. The course will:

Read more about featured speakers and organizers here.

Who: This course is appropriate for early career researchers from the fields of neuroscience, genetics, and biomedical research. Prerequisites: Basic scripting or programming knowledge is suggested but not required.

Where: 600 Main Street, Bar Harbor, Maine. Get directions with OpenStreetMap or Google Maps.

When: Oct 10-13, 2022. Add to your Google Calendar.

Requirements: Participants must bring a laptop with a Mac, Linux, or Windows operating system (not a tablet, Chromebook, etc.). They should have a few specific software packages installed (listed below).

Accessibility: We are committed to making this workshop accessible to everybody. For workshops at a physical location, the workshop organizers have checked that:

Materials will be provided in advance of the workshop and large-print handouts are available if needed by notifying the organizers in advance. If we can help making learning easier for you (e.g. sign-language interpreters, lactation facilities) please get in touch (using contact details below) and we will attempt to provide them.

Contact: Please email to-be-announced for more information.

Course description: To learn more about this course, refer to the course page at JAX.


Schedule

Monday, Oct 10

08:00 What is Behavior? Gordon Berman, Ph.D., Emory University
09:00 Keynote: Using Machine Vision and Learning to Analyze Animal Behavior Kristin Branson, Ph.D., Janelia Research Campus
10:00 Coffee/tea
10:15 Deep Learning-Based Pose Tracking Talmo Pereira, Ph.D., The Salk Institute for Biological Studies
11:15 Behavioral Analysis with Deep Learning Alexander Mathis, Ph.D., Swiss Federal Institute of Technology
12:15 Lunch
1:00 Special activities
3:00 DeepLabCut tutorial
4:30 Social LEAP Estimates Animal Poses (SLEAP) tutorial
6:00 Dinner
7:00 Evening discussion
8:30 End

Thursday, Oct 13

08:00 Detailed Behavioral Tracking and its Applications in Neuroscience Bence Olveczky, Ph.D., Harvard University
09:00 The Application of Machine Learning for Automated Quantification of Behavior Ishmail Adbus-Saboor, Ph.D., University of Pennsylvania
10:00 Coffee/tea
10:15 Quantifying Behavior in Dyadic Social Interactions Ann Kennedy, Ph.D., Northwestern University
11:15 Quantifying Worm Behaviour in Multiwell Plates: A Few Challenges, Lots of Opportunities Andre Brown, Ph.D., Imperial College London
12:15 Lunch
1:00 Special activities
3:00 Extracting Features and Detecting Actions in Pose Datasets (Python notebook)
4:40 Supervised Behavior Analysis (Python notebooks) (documentation)
6:00 Dinner
7:00 Evening discussion
8:30 End

View a more detailed schedule here.


Setup

To participate in a workshop, you will need access to software as described below. In addition, you will need an up-to-date web browser.

We maintain a list of common issues that occur during installation as a reference for instructors that may be useful on the Configuration Problems and Solutions wiki page.

Python

Python is a popular language for research computing, and great for general-purpose programming as well. Installing all of its research packages individually can be a bit difficult, so we recommend Anaconda, an all-in-one installer.

Regardless of how you choose to install it, please make sure you install Python version 3.x (e.g., 3.6 is fine).

We will teach Python using the Jupyter Notebook, a programming environment that runs in a web browser (Jupyter Notebook will be installed by Anaconda). For this to work you will need a reasonably up-to-date browser. The current versions of the Chrome, Safari and Firefox browsers are all supported (some older browsers, including Internet Explorer version 9 and below, are not).

  1. Open https://www.anaconda.com/products/individual#download-section with your web browser.
  2. Download the Anaconda for Windows installer with Python 3. (If you are not sure which version to choose, you probably want the 64-bit Graphical Installer Anaconda3-...-Windows-x86_64.exe)
  3. Install Python 3 by running the Anaconda Installer, using all of the defaults for installation except make sure to check Add Anaconda to my PATH environment variable.

Video Tutorial

  1. Open https://www.anaconda.com/products/individual#download-section with your web browser.
  2. Download the Anaconda Installer with Python 3 for macOS (you can either use the Graphical or the Command Line Installer).
  3. Install Python 3 by running the Anaconda Installer using all of the defaults for installation.

Video Tutorial

  1. Open https://www.anaconda.com/products/individual#download-section with your web browser.
  2. Download the Anaconda Installer with Python 3 for Linux.
    (The installation requires using the shell. If you aren't comfortable doing the installation yourself stop here and request help at the workshop.)
  3. Open a terminal window and navigate to the directory where the executable is downloaded (e.g., `cd ~/Downloads`).
  4. Type
    bash Anaconda3-
    and then press Tab to autocomplete the full file name. The name of file you just downloaded should appear.
  5. Press Enter (or Return depending on your keyboard). You will follow the text-only prompts. To move through the text, press Spacebar. Type yes and press enter to approve the license. Press Enter (or Return) to approve the default location for the files. Type yes and press Enter (or Return) to prepend Anaconda to your PATH (this makes the Anaconda distribution the default Python).
  6. Close the terminal window.

Data files and project organization