Professor of Computer Science, University of Bath
Toronto, Ontario
Joined July 2019
- Tweets413
- Following322
- Followers10.9K
- Likes299
Pinned Tweet
Are you (or is someone you know) teaching AI / ML / Deep Learning this year? My forthcoming book (freely available at udlbook.com) will save you a lot of time. This thread will show you why.
I've always really hated this illustration of byte-pair encoding from my book, but can't figure out how to make it better. Anyone out there got some design skills and want to have a crack at it? DM me if you are interested.
My latest tutorial for @RBCBorealis considers Neural ODEs. These extend residual networks to have an infinite number of layers, each of which makes an infinitesimal change to the data representation and underpin generative models like flow-matching.
📙 rbcborealis.com/research-blo…
Understanding Deep Learning, now published in Japanese (also available in Russian, Chinese and Korean).
・Prince: Understanding Deep Learning (MIT Press, 2023)を2分冊で全訳.オールカラー
・世界標準の教科書
・ChatGPTなど生成AIのしくみを理解するために.
・I巻では基礎となる教師あり学習からはじめ,トランスフォー…⇒深層学習を理解する I: 教師あり学習とモデルの基礎 link.amazon/B0iBQzeho
I'm gradually updating and improving chapters from Understanding Deep Learning and posting them to iclimbtrees.com .
The latest update concerns the backpropagation algorithm and network initialization. Critical info if you are teaching yourself ML!
I'm gradually updating and improving chapters from Understanding Deep Learning and posting them to iclimbtrees.com .
The latest addition considers how to find the parameters that minimize the loss. This process is known as training the model.
Ever wondered why larger learning rates and smaller batches lead to better generalization?
Part XI of the ODE/SDE in ML series for @RBCBorealis, reaveals why by treating stochastic gradient descent in the infinitesimal limit as an SDE.
rbcborealis.com/research-blo…
Over the last year, I've written 8 blogs for @RBCBorealis that will teach you everything you need to know about ODEs and SDEs for machine learning:
rbcborealis.com/blog/?topics…
Coming soon: neural ODEs, continuous normalizing flows, diffusion models, flow matching, PINNs and more.
Part 8 of my series on ODEs and SDEs in machine learning for @RBCBorealis introduces the Fokker-Planck equation and Anderson's reverse time theorem. The former maps an SDE to a PDE over a probability distribution. The latter reverses an SDE in time.
rbcborealis.com/research-blo…
Simon Prince retweeted
I’ve launched 2 new course websites for my Introduction to #ComputerVision and #DeepLearning in Computer Vision courses.
🆕 Gaussian Splatting
🆕 Flow Matching
🆕 Sparse Autoencoders
🆕 Lecture Notes (work in progress)
The videos don’t include voiceovers, but that’s coming in a future revision 🤞
Share your feedback in the thread.
I've built a new platform for learning math and AI, and I'm gradually filling it out with content. Completely free (but requires sign in). This video tells you why you should check it out. Feedback / feature requests / bug reports very welcome. Link below.
I'm updating and improving chapters from Understanding Deep Learning and posting them to iclimbtrees.com.
The latest unit describes a framework for loss functions from which least squares, binary cross-entropy, and multiclass cross-entropy losses can be derived.
🎓Announcing the 1st Bath Summer School in Machine Learning
📅 5–7 August 2026 | 📌 University of Bath
Topics: ODEs/SDEs, Bayesian methods, Self-Supervised Learning, World Models
Open to PhDs, postdocs & staff at EU/UK universities
bathmlsummerschool.org
Probability is essential for machine learning. Just added a new unit on the expectation operator which reduces a probability distribution to a single comprehensible, actionable property:
iclimbtrees.com
Completely free, and includes 43 problems with answers. Enjoy!
Here is part VI of my series of tutorials on ODEs and SDEs in machine learning for @RBCBorealis.
rbcborealis.com/research-blo…
To solve SDEs we must integrate the noise term and to this end, we develop the stochastic integral. It's solution is a stochastic process with mean zero.
I was unimpressed by online education platforms, so I built my own and am migrating "Understanding Deep Learning" onto it. Features include: animations, interactive figures, problems, notebooks, and AI integration. It's early days, but feel free to take a look! Link in replies.
You can find the website at iclimbtrees.com. You have to sign in (but it's free) and it's really only suitable for tablet or larger screens. Please send me feedback if it doesn't work for you!
Last year I wrote seven tutorials for @RBCBorealis on infinite-width neural networks. Topics included the neural tangent network, Bayesian neural networks and Neural Network Gaussian processes. Includes working code and many novel figures.
rbcborealis.com/research-blo…
This year, I've been writing a new series of articles on ODEs and SDEs for machine learning (suitable for people with zero experience of differential equations). You can find the most recent article (on closed-form solutions for ODEs) here:
rbcborealis.com/research-blo…
