Yoshua Bengio

There's only 5 days left to submit your paper! Remember, we only a short 1-page abstract

2

Get Prepared for the coming waves of Quantum Computing: Good reading : Canadian National Quantum-Readiness BEST PRACTICES AND GUIDELINES Thanks Innovation, Science and Economic Development Canada | Innovation, Sciences et Développement économique Canada

4

1 Comment

Excited to present my work next week at the #MS2Discovery Interdisciplinary Research Institute at Wilfrid Laurier University in Waterloo. The seminar will focus on my papers: 'Finding a Needle in a Haystack: A Machine Learning Framework for Anomaly Detection in Payment Systems' (https://lnkd.in/e7ch4zeW) and 'Improving the Efficiency of Payments Systems Using Quantum Computing' (https://lnkd.in/d8e8zAu2). #Payments #AI #ML #Quantum #PaymentSystems

26

Last Friday we hosted an enlightening webinar on "Understanding and Navigating Bias in Machine Learning Models" presented by Dr. Afaf Taïk, a postdoctoral researcher at Mila and Université de Montréal, specializing in responsible AI with a focus on fairness and privacy. During this webinar, Dr. Afaf Taïk delved into the categories of harms caused by unfair machine learning models, exploring the reasons behind these unfairness, which can stem from biased models or biased data. Additionally, Dr. Taïk examined various approaches to defining fairness in machine learning, emphasizing the importance of considering the consequences and context of the model's use case. Finally, Dr. Taïk discussed several techniques to avoid bias and achieve fairness, presenting the pros and cons of each strategy. 🎥 If you missed the webinar or would like to watch it again, please check the link to the recording in the comment section below. We extend our heartfelt thanks to Dr. Afaf Taïk for sharing her expertise and to all attendees for the insightful discussions at the end of the webinar. #MoroccoAI #Webinar #ArtificialIntelligence  #BiasInML #AIFairness

35

1 Comment

🎉 Thrilled to share some great news stemming from an amazing example of collaboration between UK and Greece supported by ARCHIMEDES Research on AI, Data Science, and Algorithms which will soon reach new highs thans to our partnership via the CHAI Hub. Our paper, "Benchmarking Counterfactual Image Generation," has been accepted to NeurIPS 2024 in the Datasets & Benchmarks track! We’ll present it in Vancouver on December 11th, and I couldn’t be prouder of our incredible Greek dream team of students who led this effort— Thomas Melistas Nikos Spyrou and Nefeli Gkouti. We address a critical challenge: how do we rigorously evaluate counterfactual image generation, where causal constraints must be respected, and ground truths are elusive? Our team developed a benchmarking framework that highlights the strengths of Hierarchical VAEs across diverse datasets. We’ve even made it available as a user-friendly Python package to encourage community collaboration. 🚀 Interactive demo: https://lnkd.in/e9GA5Ebu 📄 Paper: https://lnkd.in/eR2ig3pY A huge thanks to co-authors: Pedro P. Sanchez, Yannis Panagakis, Giorgos Papanastasiou, PhD, and Dr Athanasios Vlontzos. Excited to share our work with the AI community at NeurIPS. Do go and see the work and talk to this wonderful team of students. #NeurIPS2024 #GenerativeAI #Counterfactuals #CausalInference #MachineLearning #AIResearch

36

1 Comment

In our latest paper with Jean-Baptiste Waring, B.Eng., we generated a dataset on `ibm_quebec` the 127-qubit IBM Quantum System One located in Canada. The dataset contains more than 4000 experiments of long-range entanglement path qubits from 0 to 100+ qubits. The dataset and the code can be found here: https://lnkd.in/eussBW9G Paper: https://lnkd.in/ekb9Vqja A special congratulations to Jean-Baptiste Waring, B.Eng. for this repo and the quality of the experiments. #quantumcomputing

47

1 Comment

Recently, the TIGER Lab at the University of Waterloo released MMLU-Pro, a more challenging version of MMLU that includes ~10 options per question. It is a more robust and challenging massive multi-task understanding dataset, tailored to rigorously benchmark large language models' capabilities. The dataset contains 12k complex questions across various disciplines. Since the topics are mostly language-agnostic, I translated it into Italian (the translation should be of high quality) to evaluate Italian LLMs. 📂 You can access the dataset here: https://lnkd.in/ed626hgV

35

1 Comment

Check out our eChannelNews interview alongside our valued industry partner, RabbitRun Technologies Inc., discussing cybersecurity, industry-academia collaborations, and the strong commitment at the University of Ottawa and uOttawa | Faculty of Engineering | Faculté de génie to supporting such collaborations. During the interview, we also highlight some cool research by our talented PhD student, Negin Ayoughi, from the Sedna Lab (https://www.uoIoT.ca) on machine-learning-based inference of behavioural models for systematic verification of security requirements. If you are interested in the research, you can download our research paper at https://lnkd.in/eCJgjf9y. Pat Saavedra, Jaipreet S. Bindra, Shiva Nejati, Negin Ayoughi

24

🚀 Excited to present our technical paper at IEEE Quantum Week 2024 in Montréal! 🚀 Join me on Wednesday, for my presentation on "A Hybrid Quantum-Classical Physics-Informed Neural Network Architecture for Solving Quantum Optimal Control Problems" in "Quantum Machine Learning and Neural Network Architectures" session. Our work demonstrates how innovative neural network architectures can bridge the gap between quantum and classical systems to tackle complex control challenges. Looking forward to insightful discussions! See you there! 👋 #IEEEQuantumWeek2024 #QuantumMachineLearning #NeuralNetworks #QuantumComputing

7

2 Comments

Happy to share our latest paper, "𝐅𝐢𝐧𝐝𝐢𝐧𝐠 𝐚 𝐍𝐞𝐞𝐝𝐥𝐞 𝐢𝐧 𝐚 𝐇𝐚𝐲𝐬𝐭𝐚𝐜𝐤: A Machine Learning Framework for Anomaly Detection in Payment Systems", co-authored by Anneke Kosse and Jacob Sharples, now available as both the Bank of Canada (https://lnkd.in/e7ch4zeW) and the Bank for International Settlements – BIS (https://lnkd.in/eNdGE2iP) working paper. It employs a layered ML framework designed to effectively handle large volumes and address the scarcity of pre-labeled examples of anomalous transactions, providing new tools for safeguarding financial systems. #AI #machinelearning #anomalydetection #paymentsystems #transactionmonitoring

82

7 Comments

Our perspective on the potential of #liquidcrystals in #microrobotics can be found through a short story and snippet told by great researchers of my team Negar, Matthew, Cole, Ramon, and Azin University of Waterloo Faculty of Engineering https://lnkd.in/gteWyJEV

132

3 Comments

Very pleased to report that my article with Hunter Gentry, "Transitional gradation and the distinction between episodic and semantic memory", has just appeared in _Philosophical Transactions of the Royal Society B". It is also open access thanks to the new resources I have available at University of Florida, specifically an OA agreement with the UF library and the Royal Society. So everybody can see it without any shenanigans! In this article we explore various arguments against Tulving's traditional episodic/semantic memory distinction, provide them on a firmer metaphysical foundation by drawing upon the theory of natural kinds and previous things I've said about a phenomenon called "transitional gradation" in the special sciences, recommend replacing the distinction with a more dynamic life cycle of mnemonic forms of representation, and sketch some new ideas for experiments inspired by the perspective that can help arbitrate the debate over episodic memory in animals (largely Hunter's work here). Hunter was a joy to work with on this and if you see an application from him you should give it serious consideration. He's the real deal and will be publishing stuff like this for decades to come. https://lnkd.in/gPMJSV7Q

14

[Deadline July 20, 2024 IoT World Forum Special Session, 10-13 Nov 2024, Ottawa, ON, Canada] Dear colleagues, We invite you to submit your work to the IoT World Forum Special Session (SS) on Energy Efficient Computing for IoT (SEEC-IoT) https://lnkd.in/dwmXytKQ Energy efficiency stands out as a primary focus for sustainable and eco-friendly IoT networks. As data traffic and network congestion continue to escalate, IoT devices equipped with restricted computational power and energy resources face obstacles in analyzing, processing, and storing data. In response to these challenges, computing technology has surfaced as a valuable solution for preserving energy in IoT devices, offering robust computing capabilities, and streamlined storage to facilitate data collection and processing. Consequently, energy-efficient (EE) computing, also known as "green computing," has emerged as a central area of interest for researchers looking to implement IoT solutions. The proposed SEEC-IoT special session aims to bring together researchers from academia and industry to explore and present their findings in Energy- Efficient Computing Solutions for IoT. Participants are encouraged to discuss the theories, systems, technologies, and approaches used to apply those findings in real-world applications. We look forward to receiving your contributions https://lnkd.in/d8-uq4Mp Special Session Co-Chairs: Zied Bouida Kuwait College of Science and Technology Mohamed Trabelsi Kuwait College of Science and Technology Ala Abu Alkheir Lytica Inc. Anis Ben Arfi Analog Devices

15

Join Jelle Hellings and me for Ontario Database Day (https://ondbd.ca/) – a one-day symposium on all things databases, hosted at the University of Waterloo! This event brings together researchers and practitioners to explore the latest advancements in the database field. It's a great platform to showcase your work—whether it’s published or still in progress. We welcome submissions from students, postdocs, academics, and professionals in industry. Present your work, exchange ideas, and network with fellow database enthusiasts. Don’t miss the opportunity—submit your abstract by October 13th! #OntarioDatabaseDay #DatabaseResearch #DataScience #DataPrivacy #DatabaseSymposium #DatabaseCommunity #DataManagement

68

A new collaborator article is out on biostatistics.ca! Thanks to Renee (Hui Xin) Ng for sharing this insightful piece about using sophisticated Machine Learning (ML) algorithms to develop biological constructs related to brain aging. Specifically, the article explains why and how these models are biased, how to address these biases, and what they mean for research in this field. It's an fascinating read, check it out 👇 https://lnkd.in/ehKpzDsu

12

6 Comments

Quality in, Garbage out. Briefly, this recent work on Nature ( among others ) claims and gives evidence that LLMs seriously degrade their behavior if trained from LLM generated data. To the point of wreaking havoc if the process is repeated 4-5 times. This says a lot about how lossy and noisy is LLM generated content wrt the human produced training data. Not a surprise. Nice read. "We demonstrate that it must be taken seriously if we are to sustain the benefits of training from large-scale data scraped from the web. Indeed, the value of data collected about genuine human interactions with systems will be increasingly valuable in the presence of LLM-generated content in data crawled from the Internet."

65

9 Comments

In the rapidly advancing age of artificial intelligence (AI), the protection of children from potential risks has become a paramount concern on a global scale. On the 1st of October, 2024, the Association of African Universities, the University of Nottingham, and the Ethical Data Initiative held a panel discussion on Child Protection in the Age of AI as part of their Ethical Data Discussion Series. The event brought together education professionals, child protection experts, and legal experts, to discuss the pressing need to influence and shape national and international policies governing children’s safety online. It highlighted the importance of international and interdisciplinary collaboration, and evidence-based recommendations in this complex domain. The recording of the webinar is now available at https://lnkd.in/dUUdfF6b #ai #artificialintelligence

2

Exciting New Collaboration Published! 🎓 I'm thrilled to announce the release of our new paper titled "Optimizing Encoder-Only Transformers for Session-Based Recommendation Systems", a joint effort between Air Liquide and Polytechnique Montreal. This work is the foundation of the Master’s thesis by first author Anis Redjdal, M.Sc. In the paper, we introduce Sequential Masked Modeling, a novel approach to improve the performance of encoder-only transformers in session-based recommendation systems, alongside architectural improvements inspired by modern LLMs. By enhancing how transformers capture sequential dependencies, our method achieves state-of-the-art results in next-item prediction across several benchmark datasets. 🔗 https://lnkd.in/eeh6BvUg

46

3 Comments

Inventor of method that can "autonomously find properties in data and carry out tasks such as identifying specific elements in pictures", Geoffrey Hinton from the University of Toronto, together with colleague John Hopfield of Princeton University, were honoured with the 2024 Nobel Prize in Physics for discoveries and inventions that enable machine learning within artificial neural networks. Here is the official announcement: "This year’s laureates used tools from physics to construct methods that helped lay the foundation for today’s powerful machine learning. John Hopfield created a structure that can store and reconstruct information. Geoffrey Hinton invented a method that can independently discover properties in data and which has become important for the large artificial neural networks now in use." (https://lnkd.in/gq8THmzf) #nobelprize #physics #neuralnetworks #ai #data #images #machinelearning https://lnkd.in/g9k5a6tQ

1