Skip to content

Dynamics-of-Neural-Systems-Lab/Generative-modelling-reading-group

Repository files navigation

Generative-modelling-reading-group

Reading group dedicated to learning theoretical and practical foundations of GenAI, allowing us to integrate it with own research

When: Wednesdays at 11 am.

When: AI Institute meeting room.

Zoom link Deprecated, planned to be cancelled, (only if you really cannot make it in person): https://mit.zoom.us/j/97422870792.

Recording: Deprecated, planned to be cancelled, generally not recorded, ask the next presenter to record if you really cannot make it.

Important: Zoom link and recording should not be a regular excuse not to attend, and will soon become impossible.

(Exceptional permission to use zoom can be made for very long-term attendants)

Rules and guidelines

  1. We pick papers of general interest (i.e., no heavy neuro or molecular biology papers unless they truly introduce a general idea)

  2. Everyone reads the paper beforehand

  3. One person presents with slides

  4. Everyone asks questions to understand the paper

  5. We break up into groups of 2-3 and collect subjective perspectives on the topic

  6. We reconvene to share ideas and identify promising research directions

  7. Communication works via GitHub issues (one issue per paper) and discussions (everything else). Make sure to enable notifications for these two parts in the repository

  8. The presenter should moderate, i.e. steer the discussion (avoid derailing)

  9. Joel (@SeasonsOfTheSun) is permanent auxiliary moderator

  10. Outreach/Recruiting for the club is currently only word-of-mouth, we will reevaluate in the future

Structure of the club

  • ~3 month blocks
    1. Theory basics
    2. Seminal papers of the topic
    3. Applications
  • Managed democracy
    • Monthly discussions for feedback/ideas
      • GH discussion is set up in the beginning of each month and addressed at the end of the month in our meeting (15mins)
  • Have eventually brainstorming sessions / short project presentations (RELATED TO PREVIOUSLY INTRODUCED TOPICS)

Organization of ~3 months block

  • GH Discussion post to group-brainstorm the next block
  • Orga team meets to consolidate the suggestions
  • Publishing (GH post, Website, Poster, …)
  • Gathering Materials for Course
    • Joel will be responsible for this

Session structure (how does a single session look like)

  • Paper and/or code (or both) (try to get a mixture of session kinds)
  • 5 min presenter-feedback
  • 5 min organisation
    • Which next paper
    • Who does next paper

Admin team:

Joel:

  • Auxiliary chair,
  • Curating materials for making a lecture course,
  • Contribute to MedUni course registration.

Moritz:

  • General GitHub Orga.

Albert:

  • Maintain monthly GH discussion feedback,
  • Contribute to MedUni course registration.

Tips for an effective presentation

  1. Focus on the paper that was agreed on and take enough time to prepare adequately (e.g. 2+ hours every day in the week before the meeting).
  2. Say what you will say. Have an up-front slide describing the take-home messages and why the paper should be worth remembering.
  3. Link the paper to other papers (mathematically and conceptually), especially those that have already been covered in previous sessions.
  4. Either explain something properly or leave it out. This is especially true for mathematical innovations. A formula will be forgotten, but explaining the core idea and, in many cases, the proof can be very insightful.
  5. Examples, examples. Examples are essential to understanding any theory, but in ML, this is twice as true because experiments usually indicate the type of data the algorithm is designed to work on.
  6. Say what you have said. Conclude with a slide that describes how the innovations fit in the bigger picture.
  7. Raise points of discussion. If you have found something difficult to understand, chances are those bits are worth discussing.

Presenter feedback

  • 5 mins feedback in the end
  • Optional but encouraged (Joel will ask the presenter before the presentation and then enforce)
  • Purpose: Training for both (give feedback, receive feedback, improve presentation style)
  • Feedback must be positive, encouraging and constructive (e.g. sandwich technique)
  • Biscuits prize each month for best presentation (selected by Joel based on presenter feedbacks)

How to write on the screen

  • Mirror screen -> PowerPoint -> Draw in power point

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published