Research by Alan Blair, Senior Lecturer at the University of New South Wales
Professor Alan Blair, Senior Lecturer at the University of New South Wales (UNSW), is the author of more than 70 papers on the themes of co-evolutional learning, dynamic language comprehension, humanising AI, evolutional art, computational intelligence and problem solving around both games and robotics.
Co-evolutional learning, human / AI behaviour
What makes a good co-evolutionary learning environment? 1997
Coevolution of a Backgammon player 1997
Co-evolutionary learning: machines and humans schooling together 1998
Co-evolution in the successful learning of Backgammon strategy 1998
Co-evolutionary learning - lessons for human education? 1999
Co-evolution, determinism and robustness 1999
Training intelligent agents using human Internet data 1999
Effects of damage to the CDM Stroop model (comparing network damage to neurodegeneration in humans) 2000
Training intelligent agents using human data collected on the Internet 2001
Getting the job done in a hostile environment (animals behaviour in hostile environment to train agents) 2001
An improved minibrain that learns through both positive and negative feedback 2006
Evolving Plastic Neural Networks for Online Learning: Review and Future Directions 2012
Constructivist simulations for path search algorithms 2017
Dynamic language comprehension
Quasi-orthogonal maps for dynamic language recognition 1997
Analysis of dynamical recognizers 1997
Loanword formation: a neural network approach 1998
Inductive bias in context-free language learning 1998
A paradox of neural encoders and decoders or Why don't we talk backwards? 1999
Learning to predict a context-free language: Analysis of dynamics in recurrent hidden units 1999
Hill climbing in recurrent neural networks for learning the anbncn language 1999
Evolving learnable languages 2000
Representation Beyond Finite States: Alternatives to Push-Down Automata (Dynamic recurrent Networks in language (non regular, context free, context sensitive) 2001
Learning to predict the phonological structure of English loanwords in Japanese 2003
Learning the dynamics of embedded clauses 2003
Incremental training of first order recurrent neural networks to predict a context-sensitive language 2003
A structure preserving crossover in Grammatical Evolution 2005
A self-selecting crossover operator 2006 (Grammatical Evolution across a typical numeric regression problem and a typical data classification problem. Grammatical Evolution is an extension of Genetic Programming, in that it is an algorithm for evolving complete programs in an arbitrary language)
Dynamically Defined Functions in Grammatical Evolution 2006
Automated Generation of Environments to Test the General Learning Capabilities of AI Agents 2014
Humanising AI, biologically inspired
Creating Characters for Dynamic Stories in Interactive Games 2001
An improved minibrain that learns through both positive and negative feedback 2006
Complexity-based speciation and genotype representation for neuroevolution 2016
Co-Evolving line drawings with hierarchical evolution 2017
Complex image and landscape analysis, evolutional art
Distinctive feature analysis of natural landmarks as a front end for SLAM applications 2004
Texture and distinctness analysis for natural feature extraction 2005
Distinctness analysis on natural landmark descriptors 2006
Training of Recurrent Internal Symmetry Networks by Backpropagation 2009
An Abstract Deep Network for Image Classification 2012
Incremental Evolution of HERCL Programs for Robust Control (tested on benchmark classification tasks) 2014
Transgenic Evolution for Classification Tasks with HERCL 2015
Co-Evolving line drawings with hierarchical evolution 2017
Adversarial image generation using evolution and deep learning 2018
Problem solving – games and conundrums
Coevolution of a Backgammon player 1997
Why did TD-Gammon work? 1997
The evolution of subtle manoeuvres in simulated hockey 1998
Co-evolution in the successful learning of Backgammon strategy 1998
Exploring evolutionary learning in a simulated hockey environment 1999
Exploitation and peacekeeping: introducing more sophisticated interactions to the Iterated Prisoner's Dilemma 2001
Effective use of transposition tables in stochastic game tree search 2007
Learning position evaluation for Go with internal symmetry networks 2008
Bootstrapping from game tree search (learning from search) 2009
Learning a multi-player Chess game with TreeStrap 2016
Problem solving – robotics
Motion control for fast mobile robots: a trajectory-based approach 2000
Towards an efficient optimal trajectory planner for multiple mobile robots 2003
Deriving Sensor Models and Non-Linear Filtering for Exponentials of Polynomials 2007
Decentralised data fusion with exponentials of polynomials 2007
Computational Intelligence, learning and problem solving – approaches
Decentralised data fusion with exponentials of polynomials 2007
Training of Recurrent Internal Symmetry Networks by Backpropagation 2009
Bootstrapping from game tree search 2009
Learning the Caesar and Vigenere Cipher by Hierarchical Evolutionary Re-Combination 2013
Incremental Evolution of HERCL Programs for Robust Control (tested on benchmark classification tasks) 2014
Coarse and Fine Learning in Deep Networks 2014
Transgenic Evolution for Classification Tasks with HERCL 2015
Parallel Hierarchical Evolution of String Library Functions 2016
Complexity-based speciation and genotype representation for neuroevolution 2016
