+++ title = "Book and Journal Clubs" date = 2018-01-17 math = false highlight = false
[header] image = "open-book.png" caption = ""
+++
On alternate Thursdays we hold the Book Club and Journal Club.
The Book Club meet to go through a key text in Machine Learning, to help learn, and to refresh our knowledge. Typically in each session, the group works through around twenty pages of an influential book in machine learning. The sessions are led by a volunteer, and there's open discussion on the theory and topic in depth.
We are currently reading Pattern Recognition And Machine Learning by Chris Bishop, and meet every 2 weeks. Because the chapters are pretty long it will likely work best if everyone reads the chapter beforehand, and then we use the session to discuss topics we didn't fully understand, or thought were particularly interesting. A different person will lead the session each week, be in charge of doing a few things:
- Giving a short (~10 mins) summary of the key content in the chapter at the start of the session, and maybe highlighting a few key equations and plots.
- Moderating the discussion and making sure everyone has a chance to speak and ask questions.
- Deciding on the exercises for the group for that week, listing them in the exercises.md file a few days before the session, and hopefully have the solutions to hand for the session (solutions for many of the exercises in the book can be found here) and also here.
Below is the provisional schedule for the sessions and leaders (we may want to skip a few of the later chapters):
| Chapter/Section | Leader | Time / Place | Exercises | Answers |
|---|---|---|---|---|
| Sampling | Magnus Ross | 07/10/21 4pm | ||
| Sampling (11.4+, slice sampling, HMC) | Arthur Leroy | 21/10/21 4pm, G12 | ||
| TBC | TBC | 4/10/21 4pm, Ada Lovelace |
Please email me if there are any interesting ML papers you'd like to chat about in a future meeting.
Below is the provisional schedule for the sessions and leaders:
| Paper Title (link) | Leader | Time / Place | Notes |
|---|---|---|---|
| "Bayesian computing with INLA: a review." (link) | Mike Smith | 14/10/21 4pm-5pm, Ada Lovelace | |
| TBC (email me ideas!) | 28/10/21 4pm-5pm, Ada Lovelace | ||
| "Bayesian computing with INLA: a review." (second attempt!) (link) | Mike Smith | 11/11/21 4pm-5pm, Ada Lovelace | We had a lot of questions and didn't get to the end of the paper. Hopefully at this meeting we can work through the questions from last time. |
| A tutorial "PDE-constrained optimization and the adjoint method" (link | Chris Lanyon | 25/11/21 4pm-5pm, Ada Lovelace | |
| "Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm."Advances in Neural Information Processing Systems 29 (2016) (link | Magnus Ross | 10/02/22 4pm-5pm, Ada Lovelace | |
| no JC this week as Wessel Bruinsma is visiting to speak about "Meta-Learning as Prediction Map Approximation" | 24/03/22 NA | ||
| -- | Mike Smith | 10/03/22 4pm-5pm, Ada Lovelace | |
| Wilson, Andrew G., and Pavel Izmailov. "Bayesian deep learning and a probabilistic perspective of generalization." Advances in neural information processing systems 33 (2020): 4697-4708. (link) | Mike Smith | 10/03/22 4pm-5pm, Ada Lovelace |
Previous meetings can be inferred from this file's version history on github.