Skip to content

Talks

Neurosymbolic AI for Reasoning on Graph Structures

    Date: 25th March 2022
    Time: 00:00 - 00:00

    Title: Neurosymbolic AI for Reasoning on Graph Structures
    Speaker: Lauren DeLong
    Abstract:
    In this short talk, I'll present my idea for a survey paper on using neurosymbolic methods for reasoning on graph structures. Neurosymbolic methods are increasing in popularity as they combine the scalability and performance of neural network-based methods with the interpretability of symbolic methods. Subsequently, recent works have attempted to extend and apply the ideas of neurosymbolic methods to reasoning on graph structures, often for the purpose of knowledge graph completion. I will explain the ideas and motivation behind these methods, the categories to which I have classified the respective papers, and the general structure of the paper which I plan to write. I would appreciate any feedback and suggestions you might have. Additionally, if any particular sections stand out as interesting to anyone, I welcome volunteers to help co-author the paper.

    Sensing Enhancement on Complex Networks

      Date: 25th March 2022
      Time: 00:00 - 00:00

      Title: Sensing Enhancement on Complex Networks
      Speaker: Guillermo Moreno
      Abstract:
      Sensing and processing information about uncertain environments is important for survival in many types of collectives in the animal world as well as in human populations. Refining information about a complex dynamic environment is particularly important if individuals' sensing abilities are limited or information is highly complex and difficult to evaluate. In principle then, the quality of available information could be improved by pooling multiple individual estimates. However, this can also be achieved by information sharing between members of the population. Previous work has shown that communication between agents with some preference towards adopting the majority opinion can enhance the quality of error-prone individual sensing from dynamic environments. In this talk, I will show how sensing enhancement from group sensing depends on different parameters, such as the rate of sensing, the rate of change of the environment, and the type of complex networks that defines the communication channels between individuals. Numerical simulations on complex networks are complemented by a mean-field approach for limited connectivity that captures essential trends in dependencies

      Using Explainable AI to Investigate Persistent Critical Illness

        Date: 25th February 2022
        Time: 00:00 - 00:00
        Title: Using Explainable AI to Investigate Persistent Critical Illness
        Speaker: Scott O’Donoghue
        Abstract: 
        Explainable AI (XAI) techniques are now used extensively to build trust in machine learning models, but can they also be used to evaluate or add to scientific theories in the medical domain? In this project we attempt to use XAI techniques to evaluate and better understand Persistent Critical Illness, a condition that is increasingly experienced by patients admitted to the ICU.

         

        AIML 3-minute thesis competition

          Date: 10th February 2022
          Time: 00:00 - 00:00

          Title: You can survive the maze of death
          Speaker: Mark Chevallier
          Abstract:
          Every turn you take in the maze of death might lead to fortune or disaster. And you don't know which way to go! But we can prove, beyond any doubt, that by following some simple rules, you will be able to learn the absolute best way to navigate the maze. Want to know the rules? Better listen to the talk.

          Title: Proactive Side Effect Prediction: Using AI to Race Against Time
          Speaker: Lauren DeLong
          Abstract:
          Imagine going to the doctor to treat an eye infection, then ending up with itchy hives, or going for pain relief, but now your medicine causes stomach cramps! Such side effects can upset patients, dampen trust in doctors, and cost medical companies loads of money. To predict these side effects before they happen, we used network prediction methods, similar to those which generate friend recommendations for you on social media. Novel predictions can help to identify harmful side effects before a patient like you might experience them.

          Title: Prove that your car won't crash
          Speaker: Ramon Fernández-Mir
          Abstract:
          In this talk, we explain how you can convince your computer (and yourself) that an autonomous system will behave safely.

          Title:  Explaining machine answers to human questions.
          Speaker: Jorge Gaete Villegas
          Abstract:
          The field of artificial intelligence has accomplished much in recent years and its applications are everyday more embedded into our daily life. But can we really trust these systems and their predictions? Are we willing to put in the hands of a machine things like the healthcare of our loved ones? In this talk I explain our quest to provide a bridge between AI and decision makers via explanations.

          Title: Human Action Recognition
          Speaker: Zonglin Ji
          Abstract:
          Recognising human actions from a video has been considered a challenging task as it requires identifications of both spatial and temporal features to consider. In this project, I have built a classification model using deep learning that can distinguish and classify 100 plus different actions in daily life from a human skeleton-based dataset.

          Title: Euler the Mathemagician
          Speaker: Imogen Morris
          Abstract:
          Euler was infamous for using 'impossible' numbers that are smaller than any other number, yet bigger than zero, and using his almost magical intuition to arrive at the right answer, like a magician pulling a rabbit out of a hat. Using a proof-assistant, and a modern theory of infinitely-small numbers, I aim to show the real magic was in Euler's reasoning.

          Title: Trusting the Transfer: From Scotland to the Antipodes
          Speaker: Jake Palmer
          Abstract:
          Single Transferable Vote (STV) is a family of algorithms for counting ranked ballots in multi-winner elections, typically carried out by hand. We verify using a general characterisation of STV that, regardless of the existing or not-yet-existing variant used, it is correct and terminates. This extends to covering Meek's method of STV -- a computer-counting variant that relies on the convergence of a vector under iteration of a specific function -- used in several places including some elections in New Zealand.

          Title: The silent epidemic: Role of networks in tobacco control.
          Speaker: Adarsh Prabhakaran
          Abstract:
          Smoking behaviour can spread in a population through social ties. We are trying to model the spread of smoking and develop strategies to control the spread using an Agent-based model on a network.

          Title: Foundations for Physics
          Speaker: Richard Schmoetten
          Abstract:
          The physical theories describing the subatomic world have been experimentally verified to famously high degrees of accuracy. Yet conceptual problems remain: in fact, it is doubtful that the standard formulation of these theories is entirely well-defined. I aim to study one candidate remedy to these troubles, the Haag-Kastler axioms, and investigate well-founded models of reality with the help of a proof assistant.

          Title: Flowing Resources
          Speaker: Filip Smola
          Abstract:
          Resources are important to the activities we all do. We can use them to talk about what we are working with or what we are working towards. And then we can look at whole processes of activities and see how these resources flow through them. I am working to make a computer understand what we mean by these resources, so that together we can better understand the processes they control.

          Title: Here be Dragons - Navigating Formal Mathematics with Knowledge Graphs
          Speaker: James Vaughan
          Abstract:
          Unfortunately, the formal mathematics contained within interactive theorem provers is a world of its own. Although there is definite correspondence between these digitised theories and their pen-and-paper counterparts, it is not obvious to simple machines. Using knowledge graphs, we may bring back the human context to formal proofs for the benefit of both mathematicians and machines.

          Lagrangian Mechanics in Isabelle/HOL

            Date: 28th January 2022
            Time: 14:00 - 16:00

            Title: Lagrangian Mechanics in Isabelle/HOL
            Speaker: Dawson Silkenat
            Abstract: 

            Mechanics is an incredibly important branch of physics which describes motion of and interaction between particles in a system. It is widely applied in engineering fields and has a large historic role in our understanding of how the universe works. In my project I seek to provide a framework for formally proving properties of a system using the Lagrangian formulation of mechanics and a proof assistant.

            Practical Ethics and the Need for Interpretability in Biomedical AI

              Date: 28th January 2022
              Time: 14:00 - 16:00

              Title: Practical Ethics and the Need for Interpretability in Biomedical AI
              Speaker: Lauren DeLong
              Abstract: 

              I plan to submit a short essay on the need for​ interpretability in biomedical AI to the Oxford Uehiro Prize in Practical Ethics essay competition. Practical Ethics is the dialog and debate between three major facets of ethics: egoism, which is the belief that one acts in self-interest, consequentialism, in which one acts to maximize benefit for society in the future, and deontology, in which right or wrong is determined by rules beyond self-interest or societal benefit. Specifically, I use these three facets to discuss ethical dilemmas in using black-box vs. interpretable models for healthcare and medicine. I imagine this will be a 10-15 minute presentation, and I would greatly appreciate any feedback from the group regarding counterarguments, rebuttals, or important ideas which I failed to cover.

              Increasing User Engagement on the Archive of Formal Proofs

                Date: 28th January 2022
                Time: 14:00 - 16:00

                Title: Increasing User Engagement on the Archive of Formal Proofs
                Speaker: Carlin Mackenzie
                Abstract: 

                The first part of this project focused on creating a strong foundation for future development on the Archive of Formal Proofs. We now add features which encourage community growth. For example, the addition of comments allows people to discuss entries and user profiles allow people to both express themselves and see statistics about their entries. Our next steps are to evaluate our additional features with users of the AFP.

                Mechanising Newtonian Mechanics in Isabelle

                  Date: 28th January 2022
                  Time: 14:00 - 16:00

                  Title: Mechanising Newtonian Mechanics in Isabelle
                  Speaker: Lars Werne
                  Abstract: 

                  The Isabelle Theorem Prover is an interactive framework for developing formal mathematical theories that checks proofs for validity using the rules of Higher Order Logic. In my talk, I will present the state of my project on the mechanisation of Newtonian mechanics using this framework.

                  In my work thus far, I have focused on the interplay of forces acting on point particles and their position, velocity, and acceleration, based on Newton's fundamental laws of motion and previous results on abstract analysis from the Isabelle proof library. In the coming months, some of main aims will be to generalise my current implementation so that "space" is treated as an arbitrary real vector space, and expand on my results on central, conservative forces and their properties

                  AIML 3-minute thesis competition (Practice Round, Batch 2)

                    Date: 7th December 2021
                    Time: 14:00 - 16:00

                    Title: Talking About Resources
                    Speaker: Filip Smola
                    Abstract:
                    Resources control what you do, be it in what you are working with or what you are working towards. My project is to make a computer understand what we mean by these resources, so that together we can better understand the processes they control.

                    Title: Data Terms of Use, Now Automated and Forever
                    Speaker: Rui Zhao
                    Abstract:
                    Dealing with data Terms of Use (DToU) is often a shadow of modern data-processing activities, inherited from the biggest lie on the Internet -- I have read and agree to... My research proposes a novel machine-understandable language to model the DToU, to allow machines to automatically check the compliance of most data-processing activities, reducing the burdens for humans. The language is based on formal logic, taking advantages of accountability and extensibility. Last but not least, this framework acknowledges that processes can change DToU for each output data based on those for input data, and makes the compliance reasoning sustainable by deriving DToU for output data.

                    Title: Here be Dragons - Navigating Unfamiliar Mathematics using Networks
                    Speaker: James Vaughan
                    Abstract:
                    Deep learning fact selectors will learn specific representations of mathematical features to make suggestions, which need to be updated as users define new constants, types, and theories. Instead, by representing formal mathematics as a network, we can develop models that are fitted only to the network structure and generalise to any new features.

                    Title: Proactive Side Effect Prediction: Using AI to Race Against Time
                    Speaker: Lauren DeLong
                    Abstract:
                    Imagine going to the doctor to treat an eye infection, then ending up with itchy hives, or going for pain relief, but now your medicine causes stomach cramps! Such side effects can upset patients, dampen trust in doctors, and cost medical companies loads of money. To predict these side effects before they happen, we used network prediction methods, similar to those which generate friend recommendations for you on social media. Novel predictions can help to identify harmful side effects before a patient like you might experience them.

                    Title: Trusting the Transfer: From Scotland to the Antipodes
                    Speaker: Jake Palmer
                    Abstract:
                    Single Transferable Vote (STV) is a family of algorithms for counting ranked ballots in multi-winner elections, typically carried out by hand. We verify using a general characterisation of STV that, regardless of the existing or not-yet-existing variant used, it is correct and terminates. This extends to covering Meek's method of STV -- a computer-counting variant that relies on the convergence of a vector under iteration of a specific function -- used in several places including some elections in New Zealand.

                    Title: You Can Survive the Maze of Death
                    Speaker: Mark Chevallier
                    Abstract:
                    Every turn you take in the maze of death might lead to fortune or disaster. And you don't know which way to go! But we can prove, beyond any doubt, that by following some simple rules, you will be able to learn the absolute best way to navigate the maze. Want to know the rules? Better listen to the talk.

                    Title: Foundations of Physics
                    Speaker:  Richard Schmoetten
                    Abstract:
                    The physical theories describing the subatomic world have been experimentally verified to famously high degrees of accuracy. Yet conceptual problems remain: in fact, it is doubtful that the standard formulation of these theories is entirely well-defined. I aim to study one candidate remedy to these troubles, the Haag-Kastler axioms, and investigate well-founded models of reality with the help of a proof assistant.

                    Title: Follow the Patient Flow
                    Speaker: Petros Papapanagiotou
                    Abstract:
                    Hospital staff often work under a lot of pressure and have to adhere to ten of pages of policies and guidelines. They often have to improvise their workflow which leads to errors and delays that put patients at risk. Our research aims towards smart systems to model and manage patient flows, improve safety and lead to better, more consistent care.

                    AIML 3-minute thesis competition (Practice Round, Batch 1)

                      Date: 19th November 2021
                      Time: 14:00 - 16:00

                      Title: Euler the Mathemagician
                      Speaker: Imogen Morris
                      Abstract:
                      Euler was infamous for using 'impossible' numbers that are smaller than any other number, yet bigger than zero, and using his almost magical intuition to arrive at the right answer, like a magician pulling a rabbit out of a hat. Using a proof-assistant, and a modern theory of infinitely-small numbers, I aim to show the real magic was in Euler's reasoning.

                      Title: The silent epidemic: Role of networks in tobacco control
                      Speaker: Adarsh Prabhakaran
                      Abstract:
                      Smoking behaviour can spread in a population through social ties. We are trying to model the spread of smoking and develop strategies to control the spread using an Agent-based model on a network.

                      Title: Explaining machine answers to human questions
                      Speaker: Jorge Gaete-Villegas
                      Abstract:
                      The field of artificial intelligence has accomplished much in recent years and every day its applications are more embedded into our daily life. But can we really trust these systems and their predictions? Are we willing to put in the hands of a machine things like the healthcare of our loved ones? In this talk I explain our quest to provide a bridge between AI and decision makers via explanations.

                      Title: Uncertain events and Business Process Management
                      Speaker: Jiawei Zheng
                      Abstract:
                      Deviations are ubiquitous in our world, such as machine malfunction in the context of manufacturing and falling over in daily life. How to detect these deviations and provide effective interventions such as robot support when people fall to avoid further adverse effects is the main objective of my research.

                      Title: Human Action Recognition
                      Speaker: Zonglin Ji
                      Abstract:
                      Recognising human actions from a video has been considered a challenging task as it requires identifications of both spatial and temporal features to consider. In this project, I have built a classification model using deep learning that can distinguish and classify 100 plus different actions in daily life from a human skeleton-based dataset.

                      Title: Prove that your car won't crash
                      Speaker: Ramon Mir Fernández
                      Abstract:
                      In this talk, we explain how you can convince your computer (and yourself) that an autonomous system will behave safely.