Professor of Computer Science, University of Bath

Toronto, Ontario
Joined July 2019
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.
9
31
1
327
45,444
👋 CALLING ALL STUDENTS! @RBCBorealis is excited to announce our 2025 Fall Technical #Coop Program. This is your chance to work on real-world projects, build meaningful #solutions, and gain experience in #AI and #ML. View open roles & #apply by May 15: rbcborealis.com/technical-co…
1
1
4
1,947
👋 Work with us! At @RBCBorealis, we are at the forefront of #AI and #data. We build products and #technologies that shape the future of #finance and help our clients succeed. We're #hiring for various roles across our labs. #Apply now! View roles 👉 rbcborealis.com/careers/
1
2
1,479
Sampling of #deeplearning textbooks
4
5
1
46
7,060
Simon Prince retweeted
Excited to share my review of 'Understanding Deep Learning' by ⁦@SimonPrinceAI⁩! This book is a treasure trove for anyone interested in DL. It masterfully compiles the latest developments in the field, making complex concepts accessible & engaging. medium.com/@vishalvignesh/ud…
2
11
2,442
No labels? No problem. Check out how Borealis AI has been using programmatic labeling to decrease the turnaround time from a seed idea to a trained and functional machine learning model: bit.ly/2OaQKvP
Differential privacy is a mature technique that preserves the properties of a statistical distribution while making it impossible to identify an individual's #data. Our latest tutorial by @SimonPrinceAI and @marcusabrubaker explains how it works: bit.ly/3tujtfh
9
17
The final part of our #SAT solver series by @SimonPrinceAI & Christopher Srinivsa is out now! We look at solving satisfiability problems from a new angle and examine methods that allow us to apply SAT machinery to problems with continuous variables: bit.ly/35PHd3l
8
9
Borealis AI is thrilled to to announce our partnership with the @AI4Good Lab to nurture #womenintech, while promoting #AI for #socialgood. Congrats Angelique Mannella, Doina Precup & @MayaMarcusSells on the 2020 Lab! #inclusion #Diversity Read more here: bit.ly/2Bfqf1B
Simon Prince retweeted
Our latest #AItutorial is out now! Bayesian optimization is a framework that can deal with challenging optimization problems like hyperparameter search. #ML #AI @SimonPrinceAI and @MohamedOAhmed. Read it here: bit.ly/2U0W3Ov
6
11
Our latest tutorial is live! Neural Natural Language Generation - Decoding Algorithms explains how decoders translate text from one code to another by generating sequences of natural language tokens. #ML #AI #AItutorial @SimonPrinceAI @@elasri_layla ow.ly/GgBl50yXQYy
3
16
At this week’s #AAAI20, Prof. Pascal Poupart is presenting a new paper on Knowledge Graphs and how our proposed model offered state-of-the-art results for temporal knowledge graph completion. Check out the paper: bit.ly/2OIlodn and blog: bit.ly/2OFCus7 #AI
4
14
Simon Prince retweeted
Now that we’ve had some time to reflect on our time at #NeurIPS2019, our researchers put together a roundup of the papers they found to have the most impact. bit.ly/2Qt9rtn
5
2
18
Simon Prince retweeted
Where in the world would you study #ML other than Canada? 🇨🇦The Borealis AI Fellowships help domestic and international students pursue research in Canadian Universities. bit.ly/2OMkmzq
Borealis AI is proud to support a newly established #ML course offered by @MILAMontreal and @korbit_ai. The course uses AI-powered tutors, a technology that was proudly developed in #Canada by Korbit.ai. Check it out! bit.ly/2TzleWS
4
2
19
New #job alert: #NLP #research positions in Toronto, and Montreal. Apply here: bit.ly/2y7Or16. If you are at @ACL2019_Italy come by our paper "A Cross-Domain Transferable Neural Coherence Model" to learn more.
1
11
2
14
Simon Prince retweeted
If you are building ML models that consume time as a feature, check out our latest work where we show how learning a vector representation for time may improve model performance: arxiv.org/abs/1907.05321
3
29
2
123