no code implementations • 2 Jun 2023 • Yukai Qiao, Marcus Gallagher
Crossover between neural networks is considered disruptive due to the strong functional dependency between connection weights.
1 code implementation • 17 May 2023 • Jordan T. Bishop, Marcus Gallagher, Will N. Browne
Results show the system is able to effectively explore the trade-off between policy performance and complexity, and learn interpretable, high-performing policies that use as few rules as possible.
1 code implementation • 17 May 2023 • Jordan T. Bishop, Marcus Gallagher, Will N. Browne
Learning Classifier Systems (LCSs) are evolutionary machine learning systems that can be categorised as eXplainable AI (XAI) due to their rule-based nature.
Explainable Artificial Intelligence (XAI) reinforcement-learning +1
1 code implementation • 13 May 2022 • Humphrey Munn, Marcus Gallagher
Modularity is essential to many well-performing structured systems, as it is a useful means of managing complexity [8].
no code implementations • 8 Apr 2022 • Vektor Dewanto, Marcus Gallagher
We therefore propose a system of approximators for the bias (specifically, its relative value) from transient and recurrent states.
no code implementations • 19 Jan 2022 • Wai Weng Lo, Siamak Layeghy, Mohanad Sarhan, Marcus Gallagher, Marius Portmann
This paper presents a new Android malware detection method based on Graph Neural Networks (GNNs) with Jumping-Knowledge (JK).
no code implementations • 30 Sep 2021 • Mohanad Sarhan, Siamak Layeghy, Marcus Gallagher, Marius Portmann
The standard ML methodology assumes that the test samples are derived from a set of pre-observed classes used in the training phase.
no code implementations • 28 Aug 2021 • Mohanad Sarhan, Siamak Layeghy, Nour Moustafa, Marcus Gallagher, Marius Portmann
In an analysis of related works, it was observed that most researchers aim to obtain better classification results by using a set of untried combinations of Feature Reduction (FR) and Machine Learning (ML) techniques on NIDS datasets.
no code implementations • 3 Jul 2021 • Vektor Dewanto, Marcus Gallagher
In reinforcement learning (RL), the goal is to obtain an optimal policy, for which the optimality criterion is fundamentally important.
1 code implementation • 28 May 2021 • Vektor Dewanto, Marcus Gallagher
In this work, we develop a policy gradient method that optimizes the gain, then the bias (which indicates the transient performance and is important to capably select from policies with equal gain).
no code implementations • 19 Apr 2021 • Siamak Layeghy, Marcus Gallagher, Marius Portmann
Our results show that the two real-world datasets are quite similar among themselves in regards to most of the considered statistical features.
2 code implementations • 30 Mar 2021 • Wai Weng Lo, Siamak Layeghy, Mohanad Sarhan, Marcus Gallagher, Marius Portmann
This paper presents a new Network Intrusion Detection System (NIDS) based on Graph Neural Networks (GNNs).
no code implementations • 18 Oct 2020 • Vektor Dewanto, George Dunn, Ali Eshragh, Marcus Gallagher, Fred Roosta
Reinforcement learning is important part of artificial intelligence.
1 code implementation • 3 Sep 2020 • Jordan T. Bishop, Marcus Gallagher
Learning classifier systems (LCSs) are population-based predictive systems that were originally envisioned as agents to act in reinforcement learning (RL) environments.
1 code implementation • 20 Feb 2020 • Russell Tsuchida, Tim Pearce, Chris van der Heide, Fred Roosta, Marcus Gallagher
Secondly, and more generally, we analyse the fixed-point dynamics of iterated kernels corresponding to a broad range of activation functions.
1 code implementation • 29 Nov 2019 • Russell Tsuchida, Fred Roosta, Marcus Gallagher
The model resulting from partially exchangeable priors is a GP, with an additional level of inference in the sense that the prior and posterior predictive distributions require marginalisation over hyperparameters.
1 code implementation • 16 Apr 2019 • David A. Roberts, Marcus Gallagher, Thomas Taimre
In this paper we present a method for automatically deriving a Reversible Jump Markov chain Monte Carlo sampler from probabilistic programs that specify the target and proposal distributions.
no code implementations • 19 Oct 2018 • Russell Tsuchida, Fred Roosta, Marcus Gallagher
In the analysis of machine learning models, it is often convenient to assume that the parameters are IID.
no code implementations • ICML 2018 • Russell Tsuchida, Farbod Roosta-Khorasani, Marcus Gallagher
An interesting approach to analyzing neural networks that has received renewed attention is to examine the equivalent kernel of the neural network.
no code implementations • 27 Nov 2015 • Dimitri Klimenko, Hanna Kurniawati, Marcus Gallagher
In this paper, we formalize the process of classical search as a metalevel decision problem, the Abstract Search MDP.