Category: Artificial Intelligence

Privacy-Preserving Reinforcement Learning for Population Processes

July 1, 2024

We have just released another paper on arXiv: https://arxiv.org/abs/2406.17649 Here’s the abstract: We consider the problem of privacy protection in Reinforcement Learning (RL) algorithms that operate over population processes, a practical but understudied setting that includes, for example, the control of epidemics in large populations of dynamically interacting individuals. In this setting, the RL algorithm … More Privacy-Preserving Reinforcement Learning for Population Processes

Improving the Quality of the Responsible AI Conversations

June 15, 2024

I have been incredibly frustrated with the lack of quality and content in many responsible AI (RAI) conversations. Almost all the (non-academic) RAI meetings I attended these past 12 months involve the speakers repeating words like fairness, accountability, and transparency basically for the entire duration of the meeting, with everyone nodding furiously in agreement about … More Improving the Quality of the Responsible AI Conversations

Dynamic Knowledge Injection for AIXI Agents

December 9, 2023

My phd student just got a new paper accepted at the upcoming AAAI Conference on Artificial Intelligence. Here’s the abstract of the paper: Prior approximations of AIXI, a Bayesian optimality notion for general reinforcement learning, can only approximate AIXI’s Bayesian environment model using an a-priori defined set of models. This is a fundamental source of … More Dynamic Knowledge Injection for AIXI Agents

Variational Inference for Scalable 3D Object-centric Learning

October 1, 2023

My phd student has just released a paper on 3D Object-Centric Learning on arXiv. I am pretty proud of the work, although I really only understand around 40% of it. Here’s the abstract: We tackle the task of scalable unsupervised object-centric representation learning on 3D scenes. Existing approaches to object-centric representation learning show limitations in … More Variational Inference for Scalable 3D Object-centric Learning

A Simple Definition of Artificial Intelligence

August 6, 2023

There are many different definitions of Artificial Intelligence in the literature, all are suggestive and insightful. However, at the end of the day, I think there is really one simple enough to be understood and formalised rigorously. This is John McCarthy’s original definition of AI from 1955: “the science and engineering of making intelligent machines”. … More A Simple Definition of Artificial Intelligence

FinTracer and Friends

June 25, 2023

About 5 years ago, Tania Churchill and I assembled a team of researchers and engineers across AUSTRAC and ANU to work on privacy technologies for detecting criminal activities across the financial system, funded by the Fintel Alliance Expansion budget measure, the Investigative Analytics NPP (led by CSIRO’s Data61), and an ANU Translational Fellowship. The overall … More FinTracer and Friends

Split Count and Share: A Differentially Private Set Intersection Cardinality Algorithm

June 11, 2023

My colleagues Mike Purcell, Kelvin Yang Li and I have a new paper on differentially private set intersection cardinality algorithm accepted at this year’s Uncertainty in Artificial Intelligence conference. Here is the abstract:We describe a simple two-party protocol in which each party contributes a set as input. The output of the protocol is an estimate … More Split Count and Share: A Differentially Private Set Intersection Cardinality Algorithm

A Map of Machine Learning Principles and Algorithms

April 25, 2023

Here is my attempt to map out the major classes of algorithms in Machine Learning, organised around the associated induction principles and learning theory. The usual caveats apply around this being biased towards my own experience. At the highest level, we can distinguish between the Passive and Active learning settings. In the passive case, the … More A Map of Machine Learning Principles and Algorithms

A Direct Approximation of AIXI using Logical State Abstractions

October 15, 2022

Artificial Intelligence as a well-defined mathematical problem was solved a number of years ago through the formulation of the AIXI agent by Prof Marcus Hutter — see https://theconversation.com/to-create-a-super-intelligent-machine-start-with-an-equation-20756 for a quick introduction — but a key fundamental issue with the AIXI theory has always been the incomputability of the general solution. In a continuation of … More A Direct Approximation of AIXI using Logical State Abstractions