News
Mar 12, 2025
I’ll be speaking at this colloquium on “logic meets neural networks”, organised in celebration of the UNESCO world logic day.
Feb 25, 2025
We are very excited to announce that Antonio Valerio Miceli-Barone was awarded an EPSRC grant on behalf of the AI Security Institute for the project titled “Understanding and Improving the Behaviour of AI Agents in Competitive and Cooperative Games”. Shay Cohen and I are CoIs.
Feb 18, 2025
Journal paper accepted on showing that first-order clauses defined over a countably infinite domain can be reduced to propositional satisfiability under some conditions, the result is then extended to the use of function symbols also over a countably infinite set.
Jan 25, 2025
Co-chairing with Abhilekha Dalal, we are organizing a special track titled “Neurosymbolic Methods for Trustworthy and Interpretable AI” at the upcoming 19th International Conference on Neurosymbolic Learning and Reasoning (NeSy 2025). https://2025.nesyconf.org/trustworthy-interpretable/
Jan 22, 2025
happy to announce that my position paper “On the relevance of logic for AI, and the promise of neuro-symbolic learning” has been accepted for publication in Neurosymbolic Artificial Intelligence journal
Jan 6, 2025
Happy new year! Happy to report that we have several papers accepted at the International Conference on Agents and Artificial Intelligence.
Dec 23, 2024
Counterfactuals and actual causality in the situation calculus, a short paper accepted at AAMAS 2025!
Oct 31, 2024
I gave a talk on Neuro-symbolic systems for ethical AI as part of the Work in progress series at Centre for Technomoral Futures. Slides: https://zenodo.org/records/14217107
Oct 1, 2024
Last week, I presented at the Workshop on AI Vulnerabilities and their Societal Implications, organized by Atoosa (now at Carnegie Mellon University) and Des from the University of Edinburgh. My talk focused on the application of neuro-symbolic systems to ethical AI, based on my position paper at ethics and information technology.
Sep 30, 2024
Bjorn, Xue, and I are very pleased to announce that we won the best paper award at the International Conference of Learning and Reasoning in Nanjing, China. This paper, which was supported and funded by the Edinburgh Integrated AI Lab, focuses on the problem of misinformation.
Sep 5, 2024
I had the pleasure of presenting a tutorial on neuro-symbolic AI at the Logic for AI Spring School in Lake Como. Details and slides here.
Aug 22, 2024
We have 2 papers accepted on abstraction and counterfactual claims at the Conference on Learning and Reasoning, which will happen in Nanjing, China, in September 2024. We also have extended abstracts accepted on the following topics: reasoning about neural network perception, the situation calculus, and a model of implicit learning. Details here.
Jun 19, 2024
Excited to report that we have 3 acceptances at the 18th International Conference for Neurosymbolic Learning and Reasoning, happening in Barcelona in September. These invole reward machines and large language models.
May 30, 2024
I gave the keynote talk at AI Triangle workshop on Symbolic XAI – it was on logic-based loss functions.
May 28, 2024
New collaborative project with CISCO on large language models.
May 14, 2024
I had a discussion with discussion with Verve Search on ChatGPT in education.
May 1, 2024
Invited talk on Logic and learning talk at LUCI Lab, Philosophy Department, University of Milan
Apr 20, 2024
I’m happy to announce that a collaboration between the Edinburgh Futures Institute and some of us from Informatics as well as from the Robotics Institute at Heriot-Watt, we have a position paper on bringing art and AI closer together. This is not so much the case of AI-generated art, although of course it becomes a part of it, but more generally about how artistic practice could help us shape our thinking about how AI is used in society and its impact. The work appears in the mit press art journal Leonardo.
Apr 4, 2024
last year Michael Fisher, a few others, and I had conducted the Neurosymbolic and Multi-Agent Systems Workshop at AAMAS in London. One of the outcomes of that is that we decided to write a position paper on what we felt were some of the key interesting angles in this space, and this was drawn from a summary of the panel discussion at the end of this workshop. This position paper is now to appear in the proceedings of select papers from AAMAS.
Apr 3, 2024
happy to announce that Andreas’ paper on Neurosymbolic Program Induction has been accepted in the Machine Learning Journal.
Mar 22, 2024
co-organized a dagstuhl seminar on trustworthy AI via causality.
Mar 19, 2024
gave a talk on Neuro-symbolic explainability and ethics at Dagstuhl.
Mar 16, 2024
organized the foundations of neuro-symbolic AI event in Santiago, Chile.
Feb 27, 2024
did an interview on neuro-symbolic ai for the reasoner!
Feb 26, 2024
Jonathan passes his viva.
Feb 20, 2024
I co-chaired the Royal Society of UK and Royal Society of Canada Frontiers of Science Conference in Ottawa, Canada last week.
1 Jan, 2024
paper on probabilistic updates of logical representations, accepted at AAMAS-2024
1 Dec, 2023
In the past few weeks, I gave two lectures / seminars at the data science course at the Bayes Centre, as well as the topics in knowledge representation course at the University of Toronto.
Nov 16, 2023
Gave a talk at the Bayes center on explainable machine learning, diverse counterfactuals and explaining explainability to stakeholders. Based on papers 1 and 3 by Giannis.
Nov 14, 2023
A few weeks ago, I attended a very nice workshop on Safe and Robust Machine learning and gave a talk on logical loss functions.
Nov 1, 2023
Oct 31
advertising a new Postdoc position on explainability and large language models. details here: https://sigmoid.social/@vaishakbelle/111336891683472402
Oct 19, 2023
Congratulations to Ionela (Gini) Mocanu who has just passed her viva with minor corrections. Many thanks to the examiners, Loizos Michael from OU Cyprus and our own Rik Sarkar. Her thesis looked at probably approximately correct (PAC)-semantics for integrating reasoning and learning, and she has a number of results on learning to reason in linear arithmetic and temporal logic.
Oct 18, 2023
Gini and I have a new position paper accepted at the Natural Language Processing Journal, entitled “Knowledge representation and acquisition in the era of large language models: Reflections on learning to reason via PAC-Semantics.”
Oct 11, 2023
Giannis and I are excited to report that our work on diverse counterfactuals in multilinear models has been accepted for publication in the machine learning journal.
Oct 10, 2023 give a talk at the Logic and Learning series in Oslo, Norway, but also as part of the Description Logic Seminars.
Sep 27, 2023
Excited to report about a recent article I wrote for the Royal Society Open Science, where I discuss the successful integration of logic and probabilistic programming in the domains of planning and causal laws. The article is entitled: Logic + probabilistic programming + causal laws.
Sep 26, 2023
I gave a keynote talk at the inaugural workshop of Learning, Law, and Society in conjunction with ECML 2023 in Turin, Italy. Details here.
Sep 13, 2023
It was my pleasure and honor to deliver the presidential address on the engineering theme at the British Science Festival in Exeter last week!
Sep 6, 2023
Both Andreas and Giannis have cleared their PhD vivas. Congratulations to them!
30 Aug, 2023
I’ll be giving a keynote at JELIA-2023; corresponding article: Excursions in First-Order Logic and Probability: Infinitely Many Random Variables, Continuous Distributions, Recursive Programs and Beyond.
9 Aug, 2023
New article in the compendium on Neuro-symbolic AI!
8 Aug, 2023
2 papers accepted at ECAI.
June 26, 2023
I gave a long-ish seminar at the University (of Edinburgh, School of Informatics) today, covering the motivation and concepts behind my recent work with Till Hoffman, presented at AAMAS–2023. Slides.
June 10, 2023
I ran through a few slides for our NeSy AAMAS-2023 workshop to introduce folks to our mission. Check it out here.
June 6, 2023
We had Artur Garcez give a talk at the NeSy session of the Knowledge graphs workshop at the Turing.
May 23, 2023
Two papers accepted at KR-2023 on first-order logic and probability!
May 15, 2023
I’ll be giving a presidential address at the British Science Festival!
April 30, 2023
Jonathan has papers accepted at AAAI-2023, and ICML-2023 on neuro-symbolic AI. Check out his work in our papers tab.
April 28, 2023
I will be giving a talk at the Alan Turing institute on “logic and probabilistic programming”. Will share the slides soon. Here’s a blog post on it.
April 14, 2023
In a recent presentation at the NatWest Group Data Science Seminar, which took place late last month, I discussed the utility of formula-based regularizers in the context of training deep learning networks using logical formulas. Details here.
https://medium.com/@vaishakbelle/news-talk-on-formula-based-regularizers-618bc4204a1
April 13, 2023
A few weeks ago, I had the opportunity to give an invited talk on the topic of knowledge representation and ethical AI at PEEK/FWF Research Project “The Unexpected: talks on humans and AI”. Details below.
Mar 28, 2023
We have 4 papers accepted at ICLP.
Mar 25, 2023
Tia Byer did an interview with me for Oxford Global, interview video here.
Feb 27, 2023
I have a new book on robots that reason!
Feb 26, 2023
I have a new paper on knowledge representation and acquisition for ethical AI.
Feb 24, 2023
Our dagstuhl proposal for trustworthy AI through causality has been accepted.
Feb 2, 2023
We have 4 papers accepted at AAMAS. This is work with Till Hoffman, Ionela Mocanu, Daxin Liu and Brendan Juba.
Feb 1, 2023
We are excited to have Daxin Liu join our lab as a postdoctoral fellow. He is funded by the royal society fellowship, and is joining us from Aachen, where he got his phd from Prof. Gerhard Lakemeyer.
Jan 28, 2023
sentiment analysis tools and queerphobia journal paper
Automated sentiment analysis can help efficiently detect trends in patients’ moods, consumer preferences, political attitudes and more. Unfortunately, like many natural language processing techniques, sentiment analysis can show bias against marginalised groups. We illustrate this point by showing how six popular sentiment analysis tools respond to sentences about queer identities, expanding on existing work on gender, ethnicity and disability. This is joint work with Eddie, and Bjorn.
Jan 25, 2023
special issue on epistemic planning
Thomas Bolander, Andreas Herzig, Bernhard Nebel and I have written up the editorial on the special issue on epistemic planning at the Artificial Intelligence Journal.
Jan 17, 2023
blameworthiness scores learning journal paper at AAAI-2023
Wanted to congratulate Lewis for getting our journal paper on learning moral models tractably (from data mining & knowledge discovery) accepted for the AAAI-23 Journal Track.
Jan 15, 2023
ICAART-2023 position papers on deep logical induction and explainability
Jan 1, 2023
new journal on neuro-symbolic AI
As shared by Luis Lamb and Francesca Rossi, there is a new journal created for neuro symbolic AI, by Pascal, Artur and Tarek. I am excited to be part of the editorial board and receive submissions in the area.
Dec 21, 2022
Neuro-symbolic AI for Agent and Multi-Agent systems [NeSyMAS] Workshop
We are excited to be sending out the call for the Neuro-symbolic AI for Agent and Multi-Agent systems workshop at AAMAS-2023. Details here.
Dec 20, 2022
AHRC grant on responsible AI ecosystem
Very excited to be part of this team, with incredible partners and colleagues from law and philosophy, among others. Looking forward to working on responsible AI ecosystems.
Dec 18, 2022
RSE magazine piece on ethics and AI
In my RSE magazine piece, I tried to emphasise that integrating concept-based models, common-sense reasoning and well-defined human-in-the-loop systems might provide better interfaces for reasoning and contextualising ethics in systems. Legal and regulatory work is needed moreover.
Dec 1, 2022
Alan Turing Interest group in neuro-symbolic AI.
I’m part of a new Interest Group in Neuro-Symbolic AI at The Alan Turing Institute.
Nov 10, 2022
prize in argument mining task
I’d like to congratulate Xue Li and Nadin’s team who have gotten themselves second place in the argument mining task. This is exciting news! Check out the paper on validity classifiers here.
Nov 3, 2022
Paulius Dilkas has successfully defended his phd. Congrats, Paulius! He had Guy Van Den Broeck as his external and James Cheney as his internal.
Oct 18, 2022
Will be giving a talk on tractable models for ethical AI at the “The Unexpected: Talks on Humans and AI” at University of applied Arts, Vienna. Link here
Oct 12, 2022
Gave a talk on tractable models for ethical AI (based on my ICCS keynote) at the UKRI TAS Governance Node Seminar.
Oct 4, 2022
I will be giving a talk at University of South Carolina, Columbia, SC, at the Seminar in Advances in Computing. It will based on my book chapter, “Logic & Learning: From Aristotle to Neural Networks”.
Oct 3, 2022
I will be giving a talk at Bayes Fest, as the Bayes Centre celebrates turning four. It will be on “Explainability, causality and computational and-or graphs.”
Sep 14, 2022
I will be giving a keynote at ICCS on tractable probabilistic models and ethical AI. Thanks to Tanya for the invitation! Slides here
Sep 8, 2022
Will be giving a talk about ML explainability at the Pharma Data UK event. Slides here.
Aug 2, 2022
I will be giving a tutorial on logic and learning and symbolic reasoning more generally at the Oxford machine learning summer school: https://www.oxfordml.school/program-speakers
Aug 1, 2022
I gave a keynote talk at the probabilistic logic programming workshop at FLOC 2022. Thanks to Roberta and Luke for the invitation. My talk was on tractable probabilistic models, causality, and explainability. Slides here
I was also supposed to give a tutorial on logic and learning but I could not make it in person, so these slides are pre-recorded and will be uploaded soon: https://vaishakbelle.com/pages/learnfloc2022.html
July 28, 2022
Gini and Dexter Yang (who did his Msc with us) have gotten a paper on breaking Captcha using capsule nets in the journal Neural Networks. Congrats to them both. Paper here: https://doi.org/10.1016/j.neunet.2022.06.041
June 29, 2022
Advertising a fully funded PhD position on Neuro-symbolic AI and/or explainability; please apply here.
June 28, 2022
I’ll be giving a seminar the School of Business. Registration link here: https://www.eventbrite.co.uk/e/principles-and-practice-of-explainable-machine-learning-crc-tickets-370296555967
June 8, 2022
I gave a seminar at the C4AI in Sao Paolo, Brazil, as part of the “perspectives on AI” series. The talk was entitled “Principles of Explainable Machine Learning: Interpretability, Reasoning and Beyond”, link (including youtube video) here: https://c4ai.inova.usp.br/c4ai-seminar-perspectives-in-ai-prof-vaishak-belle-june-8th-2022-16h-17h30-brazil-time/
May 25, 2022
I’ll be giving an invited talk at the Trustworthy AI workshop in Belfast in June. Registration is free for this hybrid event. Link here: https://computing.ulster.ac.uk/TAI-RM2022/
May 11, 2022
Together with Efi Tsamoura and Martin Grohe, we are organizing the Samsung AI neurosymbolic workshop, June 6 — June 8, 2022. Invited speakers include Gary Marcus, Dan Roth, Abhinav Gupta and many more. Please do register to join: https://research.samsung.com/sanw
May 9, 2022
The tutorial on explainability in machine learning was given today at AAMAS-2022 virtually, and the videos are now on youtube.
May 2, 2022
We have a new journal paper out on a new type of perceptron that addresses the decades-old problem by Minsky of capturing the Boolean XOR function in a single layer. Congrats to Miguel!
May 1, 2022
I will be giving a tutorial on explainable machine learning, covering the basics, at AAMAS-2022. See the webpage for details
April 26, 2022
We have a new journal paper out on doing intention recognition with ProbLog. Congrats to Gary!
Mar 23, 2022
Our AIUK talk was live on the climate stage, with an interdisciplinary discussion between our speakers who covered themes & concepts within the New Real’s work & The New Real Observatory. Link here
Mar 18, 2022
I’ll be joining Drew Hemment from EFI to speak on AI + Arts at AIUK, the flagship conference by the Alan Turing institute. Link to event here
Mar 11, 2022
I’ll be giving a keynote at the International Workshop on Trustworthy AI for the Future of Risk Management (held in Belfast, Ulster University). Link to event here
Mar 9, 2022
Have a new article accepted at the artificial intelligence journal on analying generalized planning in the presence of nondeterminism. Generalized planning looks at the synthesis and correctness of plans with loops, program-like plans, and other branching structures. The article looks at how correctness needs to be defined in the presence of nondeterministic actions, probabilistic effects, unbounded state-action spaces, etc.
Feb 23, 2022
Advertising a postdoctoral fellowship on knowledge representation / explainable AI / neuro-symbolic systems, funded by the Royal Society.
Jan 20, 2022
The book on neuro-symbolic systems by Md and Pascal, to which I contributed a chapter on learning and logic, is out.
Jan 17, 2022
Will be co-chairing the artificial intelligence track of the UK-Tunisia Joint Conference. Co-organised by the Royal Society and the Tunisian Ministry of Higher Education and Scientific Research, and with the support of the British Council in Tunisia, the UK/Tunisia bilateral meeting for early career researchers (ECRs), the conference will take place virtually.
Dec 15, 2021
Bjorn and I are advertising a 2 year postdoc on integrating causality, reasoning and knowledge graphs for misinformation detection. See here.
Dec 1, 2021
Interested in training neural networks with logical constraints? We have a new paper that aims towards full satisfaction of Boolean and linear arithmetic constraints on training at AAAI-2022. Congrats to Nick and Rafael!
Nov 24, 2021
Gave a talk on the chapter “Logic meets Learning: From Aristotle to Neural Networks” at the doctoral training center UnRAVeL — UNcertainty and Randomness in Algorithms, VErification and Logic in Aachen (Virtual). Thanks to Joost-Pieter for the invitation! Link here
Nov 4, 2021
Sharing a preview of a book chapter, “Logic meets Learning: From Aristotle to Neural Networks”. Part of the exciting new book “Neuro-Symbolic Artificial Intelligence: The State of the Art” by Pascal Hitzler and Md Kamruzzaman Sarker.
Oct 12, 2021
We have a new artificial intelligence journal paper on multi-agent epistemic planning, with collaborators from University of Toronto, Queen’s University and University of Melbourne.
Oct 8, 2021
Interested in synthesizing the semantics of programming languages? We have a new paper on that, accepted at OOPSLA.
Sept 16, 2021
I gave an invited tutorial the Bath CDT Art-AI. I covered current trends and future trends on explainable machine learning.
Sept 9, 2021
I gave an invited talk on “Logic & Learning: From Aristotle to Neural Networks” at the AISEC annual workshop.
Sept 8, 2021
I served on an invited panel on “robotics & automation” at the Pharma Data & SmartLabs Congress, 2021.
July 6, 2021
Talk on XAI
I’ll be giving a talk on explainable AI at Lancaster University (Leipzig) Symposium on Intelligent Systems (LEISYS) on July 22.
May 17, 2021
Talk on logic & learning
Will be giving a talk on logic & learning at LMU Munich, drawing from my SUM-2020 tutorial. Thanks to Felix for the invitation!
May 16, 2021
Talk on explainable machine learning
Gave a talk this Monday in Edinburgh on the principles & practice of machine learning, covering motivations & insights from our survey paper. Key questions raised included, how to: extract intelligible explanations + modify the model to fit changing needs.
May 31, 2021
Journal paper on explainable machine learning accepted
Our work (with Giannis) surveying and distilling approaches to explainability in machine learning has been accepted. Preprint here, but the final version will be online and open access soon.
May 24, 2021
A course on explainable machine learning
I will be teaching a course on explainability machine learning, a practical introduction, supported by Andreas Bueff and others. Link here.
May 10, 2021
Two papers on probabilistic inference at UAI-2021
Jonathan’s paper considers a lifted approached to weighted model integration, including circuit construction. Paulius’ paper develops a measure-theoretic perspective on weighted model counting and proposes a way to encode conditional weights on literals analogously to conditional probabilities, which leads to significant performance improvements.
Paper on weighted model counting at SAT-2021
Weighted model counting often assumes that weights are only specified on literals, often necessitating the need to introduce auxillary variables. We consider a new approach based on psuedo-Boolean functions, leading to a more general definition. Empirically, we also get SOTA results.
May 5, 2021
Paper on learning linear programming objectives accepted at IJCAI-2021
We have a new paper accepted on learning optimal linear programming objectives. We take an “implicit“ hypothesis construction approach that yields nice theoretical bounds. Congrats to Gini and Alex on getting this paper accepted. Preprint here.
Mar 30, 2021
Dagstuhl seminar on Trustworthiness and Responsibility in AI
Sriraam, Shannon, Kush, Joost, Hana and I are excited to be organizing a dagstuhl seminar on Trustworthiness and Responsibility in AI. Link here.
Mar 25, 2021
Project on trustworthy systems
A consortia project on trustworthy systems and goverance was accepted late last year. News link here.
Mar 22, 2021
Journal paper on prior constraints in tractable models
A journal paper has been accepted on prior constraints in tractable probabilistic models, available on the papers tab. Congratulations Giannis!
Mar 21, 2021
AIUK
Will be speaking at the AIUK event on principles and practice of interpretability in machine learning.
Feb 8, 2021
KRML
Will be co-chairing a special session on knowledge representation & machine learning at KR-2021.
Jan 19, 2021
Workshop on deep learning and logic
Together with Efi, Loizos & Phokion, we are co-organising a workshop on deep learning & logic.
Jan 05, 2021
3 journal papers accepted
Three journal papers have been accepted, all on tractable probabilistic models. With Andreas and Stefanie, a continuous variant is proposed. With Michael, modeling fairness is considered. And with Lewis, the learning of moral responsibility is investigated.
Oct 22, 2020
Talk at AI, ethics & society
The talk is entitled Fairness and Moral responsibility meets Computational Tractability; link to the event here.
Oct 15, 2020
Talk at U3A
I’ll be giving a talk on responsible AI at the Edinburgh chapter of U3A. Thanks to Rod & George for the invitation.
Sep 25, 2020
Talk at the SICSA conference
I’ll be giving a talk at the conference on fair and responsible AI in the cyber physical systems session. Thanks to Ram & Christian for the invitation. Link to event.
Scotsman reports on XAI work with NatWest Group
A recent collaboration with the NatWest Group on explainable machine learning is discussed in The Scotsman. Link to article here. A preprint on the results will be made available shortly.
Lecture at FU Berlin on Fair and Responsible AI
I’ll be giving a lecture at FU Berlin on Interpretable, Fair and Responsible AI, all approached via probabilistic circuits. See the recent work with Varley, Hammond, Bueff, Papantonis, for example. Link to the class here.
Aug 17, 2020
Seminar at Heriott-Watt
I’ll be giving a seminar at the LAIV (Lab For AI Verification) at Heriott-Watt on our ECAI-2020 paper with Anton. The paper interprets variational autoencoders using probabilistic circuits. Link to event here.
Aug 8, 2020
Journal paper on Semiring programming
A journal paper has been accepted that positions a new framework we call semiring programming, which extends probabilistic programming with connectives taken from any semiring. This then allows us to capture a wide range of search and combinatorial problems considered in AI, including inference, SAT, convex programming, weighted model integration etc, in a single unified programming model. Preprint here.
Aug 3, 2020
Tutorial on Logic meets Learning in Infinite Domains
I will be giving a tutorial on logic and learning with a focus on infinite domains at this year’s SUM. Link to event here.
Aug 2, 2020
Paper at ICAPS journal track
Our paper on synthesizing plans with loops in the presence of probabilistic noise, accepted the journal of approximate reasoning, has also been accepted to the ICAPS journal track. Preprint to the full paper here.
Aug 1, 2020
Papers at KR’s recently published research track
Extended abstracts of our NeurIPS paper (on PAC-learning in first-order logic) and the journal paper on abstracting probabilistic models was accepted to KR’s recently published research track.
Jul 16, 2020
Accepted paper on logic, probability & action
A survey paper has been accepted at SUM, which looks at the semantics for integrating first-order logic, probability & action. In particular, the situation calculus, a dialect of first-order logic, is considered as the underlying representation language. Preprint here.
Jul 14, 2020
CP paper on generating random (logic) programs
Paulius’ work on algorithmic strategies for randomly generating logic programs and probabilistic logic programs has been accepted to the principles and practise of constraint programming (CP2020). The work is motivated by the need to test and evaluate inference algorithms. A combinatorial argument for the correctness of the ideas is also considered.
May 7, 2020
AKBC paper on learning credal sum-product networks
Our paper (joint with Amelie Levray) on learning credal sum-product networks has been accepted to AKBC. Such networks, along with other types of probabilistic circuits, are attractive because they guarantee that certain types of probability estimation queries can be computed in time linear in the size of the network. The problem we tackle is how the learning should be defined when there is missing or incomplete data, leading to an account based on imprecise probabilities.
May 5, 2020
Journal paper on abstracting probabilistic models
A journal paper on abstracting probabilistic models has been accepted. The paper studies the semantic constraints that allows one to abstract a complex, low-level model with a simpler, high-level one. The framework is applicable to a large class of formalisms, including probabilistic relational models. The paper also studies the synthesis problem in that context.
Mar 4, 2020
Talk at the University of Glasgow
I gave a talk on our recent NeurIPS paper in Glasgow while also covering other approaches at the intersection of logic, learning and tractability. Thanks to Oana for the invitation.
Feb 5, 2020
StarAI workshop papers
If you are attending AAAI this year, you may be interested in checking out our papers that touch on fairness, abstraction and generalized sum-product problems.
Jan 28, 2020
Journal paper on goal regression and progression with probabilities
Our work on (goal) regression and progression operators for first-order probabilistic logics will appear in Artificial Intelligence. It studies how representations in these logics behave in a dynamic setting, and introduces operators for reducing a query after actions to an initial state, or updating the representation against those actions.
Jan 15, 2020
Accepted papers at ECAI 2020
Our work on symbolically interpreting variational autoencoders, as well as a new learnability for SMT (satisfiability modulo theory) formulas got accepted at ECAI.
Dec 19, 2019
Journal paper on synthesis of recursive plans
Our work on synthesizing plans with loops in the presence of noise will appear in the international journal of approximate reasoning. It investigates how the AND-OR controller search of Hu & De Giacomo can be extended for strong goal satisfaction and termination conditions when tackling stochastic nondeterminism.
Dec 17, 2019
Talk at Simon Fraser University
Last week, I gave a talk on our NeurIPS paper on implicit learnability in FOL at SFU. Thanks to Eugenia and Jim for hosting me. Slides here.
Dec 12, 2019
NeurIPS workshop papers
If you are attending NeurIPS this year, you may be interested in checking out our papers that touch on morality, causality, and interpretability. Preprints can be found on the workshop page.
Nov 29, 2019
2019 ILP best student paper award in the long papers
We were thrilled to hear that our recent paper at ILP, entitled “Learning Probabilistic Logic Programs over Continuous Data”, received the best student paper award in the long paper track.
Nov 20, 2019
Talk at AI Center Cambridge, Samsung Research
I gave a talk on our upcoming NeurIPS paper on implicit learnability in FOL at the Samsung research center in Cambridge. Thanks to Efi for the invitation. Slides here.
Nov 8, 2019
Best paper at DeLBP 2019
We were pleased to learn that our work entitled “Implicitly Learning to Reason in First-Order Logic” was chosen as a best paper at The Fourth International Workshop on Declarative Learning Based Programming, IJCAI, 2019.
Nov 8, 2019
Academics Unplugged
Link In the last week of October, I gave a talk informally discussing explainability and ethical responsibility in artificial intelligence. Thanks to the organizers for the invitation.
Nov 5, 2019
Invited talk at the Samsung AI Forum
Event link I was very excited to be giving an invited talk at the Samsung AI Forum in Seoul today. Thanks to Samsung for the invitation and the hospitality.
Oct 22, 2019
The quest for interpretable and responsible artificial intelligence
The article, to appear in The Biochemist, surveys some of the motivations and approaches for making AI interpretable and responsible.
Oct 8, 2019
Royal Society University Research Fellow
I’m thrilled to have received the Royal Society University Research Fellowship. Announcement from the Royal Society can be found here.
Oct 2, 2019
Talk at Beyond-Symposium 2019
I gave a talk at the beyond symposium 2019, which aims to put together artists, scientists, economists, among others. The talk was on experiential AI and the challenges.
Sep 10, 2019
NeurIPS paper on PAC learnability for FOL
Brendan and I have our paper on (implicit) PAC learnability for first-order logic accepted at NeurIPS.
Sep 10, 2019
Experiential AI at Ars Electronica
Drew, Dave, Larissa and I had the opportunity to discuss the motivatons and foundations for instigating the new research theme of Experiential AI in a 90 minute talk.
Sep 6, 2019
Logic & Learning Dagstuhl Seminar
Thanks to Kristian, Michael, Phokion and Daniel for organizing a great seminar at the Dagstuhl. Along with the discussions, I had an opportunity to reflect on the ways logic ehances learning. Slides on a short presentation I gave, entitled six perspectives on logic & learning (in infinite domains) can be found here.
Aug 12, 2019
Experiential AI editorial at Leonardo
Paper link Drew, Ruth, Larissa, Dave, Frank and I have an editorial accepted on experiential AI at the Leonardo journal
Aug 6, 2019
Talk at the Skeptics on the Fringe
Link I gave a talk at the Skeptics on the Fringe on ethical AI. Thanks to the Edinburgh Skeptics for the invitation.
Jul 30, 2019
Paper accepted on program induction
The paper tackles unsupervised program induction over mixed discrete-continuous data, and is accepted at ILP.
Jul 19, 2019
Seminar at NII
Last week, I gave a seminar at NII in Tokyoon our recent work on interpretable and responsible AI. Thanks to Katsumi Inoue for organising the talk.
Jul 4, 2019
Seminar at IISC
I gave a seminar at the Indian Institute of Science on our recent work on interpretable and ethical AI. Thanks to Partha Talukdar for organising the talk.
Jun 21, 2019
CogRobo Seminar
Seminar link I gave a seminar at the Sabancı University in Turkey on our recent work on interpretable and ethical AI. Thanks to Esra Erdem for organising the talk.
May 30, 2019
EPSRC IAA grant for Credit Risk
Link Raffaella and I are thrilled to receive an EPSRC IAA grant on “AI for credit risk.”
May 29, 2019
Adventures with a Robot
Last week, I gave a talk at the pint of science on automated systems and their impact, touching on the topics of fairness and blameworthiness.
May 18, 2019
ZKM Center for Art and Media
Larissa, Drew, Dave and I are excited to be giving a talk on experiential AI at the ZKM Center for Art and Media Karlsruhe.
May 14, 2019
Experiential AI: a new research agenda in which artists and scientists come together
Together with colleagues from Edinburgh and Herriot Watt, we have put out the call for a new research agenda.
Oct 30, 2018
Tutorial on unifying logic, probability and dynamics
I gave the tutorial at the 16th International Conference on Principles of Knowledge Representation and Reasoning / KR 2018.
Oct 28, 2018
Probabilistic Planning by Probabilistic Programming Talk
I gave a talk at the Cognitive Robotics Workshop at KR-18, entitled Probabilistic Planning by Probabilistic Programming: Semantics, Inference and Learning.
Oct 24, 2018
Towards Intepretable & Responsible AI
I gave a talk at the London Machine Learning Meetup. Thanks to the organizers for the invitation.
Aug 28, 2018
ACAI 2018: Summer school on statistical relational AI
I gave at a tutorial on effective inference and learning with probabilistic logical models in continuous domains, at ACAI 2018.
Jul 13, 2018
IJCAI-ECAI 2018 Workshop on Learning & Reasoning
We are organising a workshop on integrating learning and reasoning at IJCAI-ECAI in Sweden.
Jul 11, 2018
RSE YAS member
I’m thrilled to become a member of the Royal Society of Edinburgh (RSE) Young Academy of Scotland.
Jun 27, 2018
New AIJ article accepted
The article introduces a general logical framework for reasoning about discrete and continuous probabilistic models in dynamical domains.
Jun 2, 2018
The End of Privacy 1.0: Data Portability and Information Rights
I gave a talk, entitled “Explainability as a service”, at the above event that discussed expectations regarding explainable AI and how could be enabled in applications.
May 1, 2018
Paper accepted at IJCAI-18
In the paper, we exploit the XADD data structure to perform probabilistic inference in mixed discrete-continuous spaces efficiently.
Apr 21, 2018
Presentation at ICAPS-18 Journal Track
Our MLJ (2017) article on planning with hybrid MDPs was accepted for presentation at the journal track.
Apr 13, 2018
Seminar at Ben-Gurion University
I gave a seminar on decision-theoretic planning via probabilistic programming, based on our recent MLJ (2017) article.
Mar 23, 2018
EPSRC: Towards Explainable and Robust Statistical AI
I’m thrilled to soon get started on a EPSRC first grant on XAI.
Mar 21, 2018
Deloitte Datathon
Through the Alan Turing Institute, we (Stefanie, Andreas and I) mentored at the Deloitte Datathon, on the theme of financial services for social good.
Mar 18, 2018
IPAB Seminar
Last week, I gave an IPAB (Edinburgh) seminar on decision-theoretic planning via probabilistic programming, based on our recent MLJ (2017) article.
Mar 15, 2018
SMiLe 2018
I attended the SML workshop in the Black Forest, and talked about the connections between explainable AI and statistical relational learning.
Feb 23, 2018
Building Trust in AI Workshop
I gave a talk entitled “Perspectives on Explainable AI,” at an interdisciplinary workshop focusing on building trust in AI.
Feb 8, 2018
Probabilistic Planning by Probabilistic Programming
An article at the planning and inference workshop at AAAI-18 compares two distinct approaches for probabilistic planning by means of probabilistic programming.
Jan 25, 2018
Paper accepted at AAMAS-18
The paper discusses the epistemic formalisation of generalised planning in the presence of noisy acting and sensing.
Nov 16, 2017
Interpretability of Algorithmic Systems Workshop
I gave a talk at the workshop on how the synthesis of logic and machine learning, especially areas such as statistical relational learning, can enable interpretability.
Nov 13, 2017
Talk at the University of Oxford
I gave a talk on decision-theoretic planning via probabilistic programming at Oxford.
Nov 7, 2017
Hybrid Reasoning for Intelligent Systems, 2017
I gave a talk and a tutorial at the Hybrid reasoning workshop at Aachen, Germany.
Nov 2, 2017
PhD position on Explainable AI, KR and ML
Applications are invited for a PhD position in Artificial Intelligence, to be based in the School of Informatics at the University of Edinburgh.
Nov 1, 2017
Turing Faculty Fellow
I’m thrilled to be a faculty fellow at the Alan Turing Institute.
Oct 31, 2017
Seminar on First-order probabilistic relational models
I gave a seminar on extending the expressiveness of probabilistic relational models with first-order features, such as universal quantification over infinite domains.
Oct 6, 2017
Machine learning Journal article
We study planning in relational Markov decision processes involving discrete and continuous states and actions, and an unknown number of objects (via probabilistic programming).
Aug 15, 2017
Tutorial on First-Order Multi-agent Logics in Action
I’m giving a tutorial on First-Order Multi-agent Logics in Action at IJCAI in Melbourne, Australia.
Aug 12, 2017
Tutorial on Unifying Logic, Dynamics and Probability
I’m giving a tutorial on Unifying Logic, Dynamics and Probability — Foundations, Algorithms and Challenges at IJCAI in Melbourne, Australia.
Jul 3, 2017
Paper accepted at UAI 2017
The paper discusses how to handle nested functions and quantification in relational probabilistic graphical models.
Jun 13, 2017
Talk at the Amsterdam Machine Learning Lab
I discussed advances in open-universe probabilistic models.
Jun 12, 2017
Dagstuhl seminar on epistemic planning
I attended a workshop on epistemic planning, where I presented a poster on some results pertaining to programs in unbounded stochastic domains.
Jun 1, 2017
IJCAI 2017 Workshop on Logical Foundations for Uncertainty and Learning
Henri, Lluis, Guilin, James, Marcelo and I are organising a workshop on the logical foundations of uncertainty and learning.
May 5, 2017
IJCAI-17 Early Career Spotlight Track
Honored to be giving a talk at the IJCAI-17 Early Career Spotlight track.
Apr 24, 2017
2 papers accepted at IJCAI 2017
The first introduces a first-order language for reasoning about probabilities in dynamical domains, and the second considers the automated solving of probability problems specified in natural language.
Apr 7, 2017
Seminar at MIT
I went over symbolic approaches to probabilistic inference and optimisation.
Mar 9, 2017
ICAPS 2017 Workshop on Generalized Planning
Siddharth, Sheila, Ron and I are organizing a workshop on generalized planning to be held at ICAPS.
Mar 5, 2017
Edinburgh University International Development Society (EUID)
I gave a talk on the risks of artificial intelligence and research priorities at the International Development Society.
Feb 22, 2017
Talk at the University of York
I discussed model counting approaches for mixed discrete-continuous probability spaces.
Nov 13, 2016
2 papers accepted at AAAI-17
These introduce (1) the use of symbolic representations in solving logical linear programs, and (2) an extension of weighted model counting for open universes.
Nov 1, 2016
AAAI-17 Workshop on Symbolic Inference and Optimization
Optimization Scott, Rodrigo, Kristian, Martin and me are organizing a workshop to explore and promote symbolic approaches to probabilistic inference, numerical optimization and machine learning.
Sep 30, 2016
Moved to the University of Edinburgh
Since October, I am at the University of Edinburgh.
Apr 20, 2016
Invited paper at IJCAI-16
An abridged version of our UAI-15 paper on approximate inference will be presented in the sister conferences track at IJCAI-16.
Jan 29, 2016
Paper accepted at KR-16
We consider the question of how generalized plans (plans with loops) can be deemed correct in unbounded and continuous domains.
Dec 1, 2015
2 papers accepted at AAAI-16
These introduce (1) component caching in hybrid domains, and (2) a first-order logic of probability with only knowing.
Sep 3, 2015
Machine Learning Journal Award at ECML-PKDD
Our Paper Planning in Discrete and Continuous Markov Decision Processes by Probabilistic Programming received the best student paper award at ECML-PKDD.
Jul 31, 2015
4 papers accepted at IJCAI-15
We have 4 papers accepted at IJCAI-15. These cover (1) weighted model counting for hybrid domains, (2) the GOLOG language in hybrid domains, (3) interactions between only knowing and common knowledge, and (4) only knowing defined in classical modal logic.
Jul 16, 2015
Microsoft Best Paper Award at UAI
Our Paper Hashing-Based Approximate Probabilistic Inference in Hybrid Domains received the best paper award at 31st Conference on Uncertainty in Artificial Intelligence (UAI), 2015.
Nov 1, 2014
Moved to KU Leuven
Since November, I am a postdoctoral researcher at KU Leuven.
Jul 28, 2014
2 papers accepted at AAAI-14
We introduce (a) PREGO, an action language for cognitive robotics in continuous domains, and (b) computing compact conditional plans in partially observable domains.
Jul 21, 2014
2 papers accepted at KR-14
We address the progression of basic action theories in (a) multiagent systems and (b) stochastic domains.
Jun 19, 2014
Silver medal by the Kurt Gödel Society
My project on cognitive robotics was selected as a finalist for the Kurt Gödel Research Prize Fellowship, receiving a silver medal by the Kurt Gödel Society.
May 29, 2014
Heidelberg Laureate Forum
I have been selected to participate in the Heidelberg Laureate Forum, where I will meet with Abel, Fields and Turing Laureates.
May 13, 2014
Paper accepted at AAMAS-14
We introduce a rich account of robot localization.
Feb 17, 2014
Summer Research Project in Knowledge Representation
We are offering a summer research project in knowledge representation.
Jan 1, 2014
CSC 2502/486: Knowledge Representation
This Winter, I will be teaching CSC 2502/486 Knowledge Representation and Reasoning.