-
Chapter and Conference Paper
Unsupervised Representation Learning via Information Compression
This paper explores a new paradigm for decomposing an image by seeking a compressed representation of the image through an information bottleneck. The compression is achieved iteratively by refining the recons...
-
Chapter and Conference Paper
Compositing Foreground and Background Using Variational Autoencoders
We consider the problem of composing images by combining an arbitrary foreground object to some background. To achieve this we use a factorized latent space. Thus we introduce a model called the “Background an...
-
Chapter and Conference Paper
A Method of Integrating Spatial Proteomics and Protein-Protein Interaction Network Data
The increase in quantity of spatial proteomics data requires a range of analytical techniques to effectively analyse the data. We provide a method of integrating spatial proteomics data together with protein-p...
-
Chapter and Conference Paper
Extended Formulations for Online Action Selection on Big Action Sets
There are big data applications where there is an abundance of latent structure in the data. The online action selection learning algorithms in the literature use an exponential weighting for action selection....
-
Chapter and Conference Paper
Non-Negative Matrix Factorization with Exogenous Inputs for Modeling Financial Data
Non-negative matrix factorization (NMF) is an effective dimensionality reduction technique that extracts useful latent spaces from positive value data matrices. Constraining the factors to be positive values, ...
-
Article
Quadratic assignment problem: a landscape analysis
The anatomy of the fitness landscape for the quadratic assignment problem is studied in this paper. We study the properties of both random problems, and real-world problems. Using auto-correlation as a measur...
-
Article
Renormalisation of 2D Cellular Automata with an Absorbing State
We describe a real-space renormalisation scheme for non-equilibrium probabilistic cellular automata (PCA) models, and apply it to a two-dimensional binary PCA. An exact renormalisation scheme is rare, and ther...
-
Chapter and Conference Paper
Ising Bandits with Side Information
We develop an online learning algorithm for bandits on a graph with side information where there is an underlying Ising distribution over the vertices at low temperatures. We are motivated from practical setti...
-
Chapter and Conference Paper
Experiments in Bayesian Recommendation
The performance of collaborative filtering recommender systems can suffer when data is sparse, for example in distributed situations. In addition popular algorithms such as memory-based collaborative filtering...
-
Chapter and Conference Paper
Improving Performance in Combinatorial Optimisation Using Averaging and Clustering
In a recent paper an algorithm for solving MAX-SAT was proposed which worked by clustering good solutions and restarting the search from the closest feasible solutions. This was shown to be an extremely effect...
-
Article
Open AccessAn evolutionary method for learning HMM structure: prediction of protein secondary structure
The prediction of the secondary structure of proteins is one of the most studied problems in bioinformatics. Despite their success in many problems of biological sequence analysis, Hidden Markov Models (HMMs) ...
-
Article
Thermal equivalence of DNA duplexes without calculation of melting temperature
The common key to nearly all processes involving DNA is the hybridization and melting of the double helix: from transmission of genetic information and RNA transcription, to polymerase chain reaction and DNA m...
-
Chapter and Conference Paper
A Distributed Approach to Musical Composition
Current techniques for automated composition use a single algorithm, focusing on one aspect of musical generation. In our system we make use of several algorithms, distributed using an agent oriented middlewar...
-
Chapter and Conference Paper
The Block Hidden Markov Model for Biological Sequence Analysis
The Hidden Markov Models (HMMs) are widely used for biological sequence analysis because of their ability to incorporate biological information in their structure. An automatic means of optimising the structur...
-
Chapter and Conference Paper
A Data Clustering and Streamline Reduction Method for 3D MR Flow Vector Field Simplification
With the increasing capability of MR imaging and Computational Fluid Dynamics (CFD) techniques, a significant amount of data related to the haemodynamics of the cardiovascular systems are being generated. Dire...
-
Article
Genetic Algorithm for Graph Coloring: Exploration of Galinier and Hao's Algorithm
This paper examines the best current algorithm for solving the Chromatic Number Problem, due to Galinier and Hao (Journal of Combinatorial Optimization, vol. 3, no. 4, pp. 379–397, 1999). The algorithm combines a...
-
Chapter and Conference Paper
Barrier Trees For Search Analysis
The development of genetic algorithms has been hampered by the lack of theory describing their behaviour, particularly on complex fitness landscapes. Here we propose a method for visualising and analysing the ...
-
Chapter
A Statistical Mechanics Analysis of Genetic Algorithms for Search and Learning
Statistical mechanics can be used to derive a set of equations describing the evolution of a genetic algorithm involving crossover, mutation and selection. This paper gives an introduction to this work. It is ...
-
Chapter and Conference Paper
Maximum Entropy Analysis of Genetic Algorithms
Genetic algorithms are widely-used search techniques which have been applied to many problems in optimization, machine learning, design, and many other domains. However, genetic algorithms are not well-underst...
-
Chapter and Conference Paper
Maximum entropy analysis of genetic algorithm operators
A maximum entropy approach is used to derive a set of equations describing the evolution of a genetic algorithm involving crossover, mutation and selection. The problem is formulated in terms of cumulants of t...