Mrs Aneta Neumann
Aneta Neumann graduated from the Christian-Albrechts-University of Kiel, Germany in Computer Science and is currently undertaking postgraduate research at the School of Computer Science, the University of Adelaide, Australia. She was a participant in the SALA 2016 and 2017 exhibitions in Adelaide and has presented invited talks at UCL London, Goldsmiths, University of London, the University of Nottingham and the University of Sheffield in 2016 and 2017. Aneta is a co-designer and co-lecturer for the EdX Big Data Fundamentals course in the Big Data MicroMasters® program. Her main research interest is understanding the fundamental link between bio-inspired computation and digital art.
Supervisors: Dr. Bradley Alexander and Prof. Zbigniew Michalewicz
Tutorial on Evolutionary Computation for Digital Art at GECCO 2018
Tutorial on Evolutionary Computation for Digital Art with Frank Neumann accepted at Genetic and Evolutionary Computation Conference (GECCO) 2018.
Big Data Fundamentals MOOC's course
Aneta is a co-designer and co-lecturer for Big Data Fundamentals course in the Big Data MicroMasters® program, an open online graduate level series of courses https://blogs.adelaide.edu.au/adelaidex/2017/05/24/adelaidex-launches-big-data-micromasters/.
Cover Page on SIGEVOlution
SIGEVOlution newsletter of the ACM Special Interest Group on Genetic and Evolutionary Computation, Volume 10, Issue 3, http://www.sigevolution.org/issues/SIGEVOlution1003.pdf
CS Researcher in SALA Art Exhibition
Aneta Neumann, a researcher from the School of Computer Science is exhibiting two mixed media artworks in Hub Central. The artworks are inspired by images produced by new methods in evolutionary image transition, pioneered by Aneta in her research toward her PhD.This research carried out within the Optimisation and Logistic Research Group in the School explores the fundamental link between evolutionary processes and generative art. The images will be on display in the Hub until the 18th of August. http://blogs.adelaide.edu.au/cs/2017/08/15/cs-researcher-in-sala-art-exhibition/
evolutionary computation, generative art, multi-objective optimisation, diversity,
machine learning, aesthetic measure, features, deep learning
Poster Presentation - Ingenuity 2016 - Faculty of Engineering, Computer and Mathematical Science
Quasi-random Agents for Image Transition and Animation
Authors: Aneta Neumann, Frank Neumann, Tobias Friedrich
ABSTRACT: Quasi-random walks show similar features as standard random walks, but with much less randomness. We utilize this established model from discrete mathematics and show how agents carrying out quasi-random walks can be used for image transition and animation. The key idea is to generalize the notion of quasi-random walks and let a set of autonomous agents perform quasi-random walks painting an image. Each agent has one particular target image that they paint when following a sequence of directions for their quasi-random walk. The sequence can easily be chosen by an artist and allows them to produce a wide range of different transition patterns and animations.
Evolutionary Image Composition Using Feature Covariance Matrices
Authors: Aneta Neumann, Zygmunt L Szpak, Wojciech Chojnacki, Frank Neumann
ABSTRACT: Evolutionary algorithms have recently been used to create a wide range of artistic work. In this paper, we propose a new approach for the composition of new images from existing ones, that retain some salient features of the original images. We introduce evolutionary algorithms that create new images based on a fitness function that incorporates feature covariance matrices associated with different parts of the images. This approach is very flexible in that it can work with a wide range of features and enables targeting specific regions in the images. For the creation of the new images, we propose a population-based evolutionary algorithm with mutation and crossover operators based on random walks. Our experimental results reveal a spectrum of aesthetically pleasing images that can be obtained with the aid of our evolutionary process.
Evolution of Artistic Image Variants Through Feature Based Diversity Optimisation
Authors: Bradley Alexander, James Kortman, Aneta Neumann
ABSTRACT: Measures aimed to improve the diversity of images and image features in evolutionary art help to direct search toward more novel and creative parts of the artistic search domain. To date such measures have focused on relatively indirect means of ensuring diversity in the context of search to maximise an aesthetic or similarity metric. In recent work on TSP problem instance classification, selection based on a direct measure of each individual's contribution to diversity was successfully used to generate hard and easy TSP instances. In this work we use an analogous search framework to evolve diverse variants of a source image in one and two feature dimensions. The resulting images show the spectrum of effects from transforming images to score across the range of each feature. The evolutionary process also reveals interesting correlations between feature values in both one and two dimensions.
Multi-objectiveness in the Single-objective Traveling Thief Problem
Authors: Mohamed El Yafrani, Shelvin Chand, Aneta Neumann, Belaid Ahiod, Markus Wagner
ABSTRACT: Multi-component problems are optimization problems that are composed of multiple interacting sub-problems. The motivation of this work is to investigate whether it can be better to consider multiple objectives when dealing with multiple interdependent components. Therefore, the Travelling Thief Problem, a relatively new benchmark problem, is investigated as a bi-objective problem. An NSGA-II adaptation for the bi-objective model is compared to three of the best known algorithms for the original single-objective problem. The results show that our approach generates diverse sets of solutions, while being competitive with the state-of-the-art single-objective algorithms.
Evolutionary Image Transition Using Random Walks
Authors: Aneta Neumann, Bradley Alexander, Frank Neumann
ABSTRACT: We present a study demonstrating how random walk algorithms can be used for evolutionary image transition. We design different mutation operators based on uniform and biased random walks and study how their combination with a baseline mutation operator can lead to interesting image transition processes in terms of visual effects and artistic features. Using feature-based analysis we investigate the evolutionary image transition behaviour with respect to different features and evaluate the images constructed during the image transition process.
A Modified Indicator-based Evolutionary Algorithm (mIBEA)
Authors: Li,W, Ozcan,E, John,R, Drake,JH, Neumann,A, Wagner,M, 2017
ABSTRACT: Multi-objective evolutionary algorithms (MOEAs) based on the concept of Pareto-dominance have been successfully applied to many real-world optimisation problems. Recently, research interest has shifted towards indicator-based methods to guide the search process towards a good set of trade-off solutions. One commonly used approach of this nature is the indicator-based evolutionary algorithm (IBEA). In this study, we highlight the solution distribution issues within IBEA and propose a modification of the original approach by embedding an additional Pareto-dominance based component for selection. The improved performance of the proposed modified IBEA (mIBEA) is empirically demonstrated on the well-known DTLZ set of benchmark functions. Our results show that mIBEA achieves comparable or better hypervolume indicator values and epsilon approximation values in the vast majority of our cases (13 out of 14 under the same default settings) on DTLZ1-7. The modification also results in an over 8-fold speed-up for larger populations.
The Evolutionary Process of Image Transition in Conjunction with Box and Strip Mutation
Authors: Aneta Neumann, Bradley Alexander, Frank Neumann
ABSTRACT: Evolutionary algorithms have been used in many ways to generate digital art.We study how the evolutionary processes can be used for evolutionary art and present a new approach to the transition of images. Our main idea is to define evolutionary processes for digital image transition, combining different variants of mutation and evolutionary mechanisms. We introduce box and strip mutation operators which are specifically designed for image transition. Our experimental results show that the process of an evolutionary algorithm in combination with these mutation operators can be used as a valuable way to produce unique generative art.
Evolutionary Image Transition Based on Theoretical Insights of Random Processes [download]
Authors: Aneta Neumann, Bradley Alexander, Frank Neumann
ABSTRACT: Evolutionary algorithms have been widely studied from a theoretical perspective. In particular, the area of runtime analysis has contributed significantly to a theoretical understanding and provided insights into the working behaviour of these algorithms. We study how these insights into evolutionary processes can be used for evolutionary art. We introduce the notion of evolutionary image transition which transfers a given starting image into a target image through an evolutionary process. Combining standard mutation effects known from the optimization of the classical benchmark function OneMax and different variants of random walks, we present ways of performing evolutionary image transition with different artistic effects.
Invited lectures/talks/scientific visit:
- Goldsmiths, University of London, Nov 2017
- The scientific visit at Mixed Reality Laboratory at the University of Nottingham, UK, Oct/Nov 2017
- University of Sheffield, Oct 2017
- The scientific visit at Algorithm Engineering Group at the Hasso Plattner Institute, Potsdam, Germany, Apr/Mai 2017
- Goldsmiths, University of London, Dec 2016
- University College, London, Dec 2016
- University of Sheffield, Dec 2016
- University of Nottingham, Nov 2016
Conference Programme Committee/Student Member:
- Association for Computing Machinery Membership, 2017
- IEEE Computational Intelligence Society Membership, 2017
- IEEE Theoretical Foundations of Bio-inspired Computation Task Force, 2017
- Australasian Conference On Artificial Life and Computational Intelligence, 2016
- ECMS Volunteer & Ambassador Program, 2016, 2017
Presentations and exhibitions:
- SALA, South Australia Living Artists Festival, August 2016
If you have any questions about my work or suggestions for this webpage, please send me an email.
Entry last updated: 4 January 2018
|2016||PhD Candidate||University of Adelaide|
|English||Can peer review|
|German||Can peer review|
|Polish||Can peer review|
|2007||Kiel University||Germany||Diplom in Computer Science (Dipl.Inf.)|
|Technical University of Dortmund||Germany||Vordiplom in Computer Science|
|Introduction to University Teaching||University of Adelaide||Australia|
|2017||Neumann, A., Alexander, B. & Neumann, F. (2017). Evolutionary Image Transition Using Random Walks. Proc. 6th Int. Conf. Evolutionary and Biologically Inspired Music, Sound, Art and Design (EvoMUSART’17). Amsterdam.
|2017||Neumann, A., Szpak, Z. L., Chojnacki, W. & Neumann, F. (2017). Evolutionary Image Composition Using Feature Covariance Matrices. The Genetic and Evolutionary Computation Conference (GECCO 2017). Germany.|
|2017||Neumann, A., Szpak, Z., Chojnacki, W. & Neumann, F. (2017). Evolutionary image composition using feature covariance matrices. The Genetic and Evolutionary Computation Conference (GECCO 2017). Berlin, Germany.
|2017||Alexander, B., Kortman, J. & Neumann, A. (2017). Evolution of artistic image variants through feature based diversity optimisation.
|2017||Li, W., Ozcan, E., John, R., Drake, J., Neumann, A. & Wagner, M. (2017). A Modified Indicator-based Evolutionary Algorithm (mIBEA). IEEE Congress on Evolutionary Computation 2017. San Sebastián.
|2016||Neumann, A., Alexander, B. & Neumann, F. (2016). The evolutionary process of image transition in conjunction with box and strip mutation. The 23rd International Conference on Neural Information Processing (ICONIP 2016). Kyoto, Japan.
|2017||Neumann,; (2017); ART EXHIBITION SALA 2017, THE UNIVERSITY OF ADELAIDE, the South Australian Living Arts Festival 2017; Adelaide;|
|2016||Neumann, A.; (2016); ART EXHIBITION SALA 2016, THE UNIVERSITY OF ADELAIDE STUDENT ART EXHIBITION, the South Australian Living Arts Festival 2016 (SALA2016); ADELAIDE;|
|2016||Neumann, A., Alexander, B. & Neumann, F.; (2016); The Evolutionary Process of Image Transition in Conjunction with Box and Strip Mutation;|
|2016||Neumann, A., Alexander, B. & Neumann, F.; (2016); Evolutionary Image Transition Based on Theoretical Insights of Random Processes.;|
2017 ACM Travel Grant,
2017 EvoStar Travel Bursaries Award,
2016 School of Computer Science Postgraduate Scholarship, University of Adelaide, Australia
- 2017, EdX MOOC, co-designer and co-lecturer Big Data Fundamentals, MicroMasters
- 2017, Lecturer, Foundations of Computer Science, Master of Computing and Innovation, Sem 1, 6 Units
- 2017, University of Adelaide, School of Computer Science, Australia, Areas: Supervisor: Introduction to Programming Processing, EdX Course: Think. Create. Code, Sem 1
- 2016, University of Adelaide, School of Computer Science, Australia, Areas: Supervisor: Introduction to Programming Processing, EdX Course: Think. Create. Code, Sem 2
- 2012, University of Adelaide, School of Computer Science, Australia, Areas: Supervisor: Object-oriented programming in Java
- 2012, University of Adelaide, School of Computer Science, Australia, Areas: Supervisor: Internet Computing
- 2011, University of Adelaide, School of Computer Science, Australia, Areas: Supervisor: Object-oriented programming in Java
- 2011, University of Adelaide, School of Computer Science, Australia, Areas: Supervisor: Introduction to programming for engineers (Matlab/C)
- 2008, University of Applied Sciences, Saarbruecken, Germany, Areas: Lecturer for Software Technology and Programming in Java
2017-2018, Christo Pyromallis, Computer Science Student and Winner of ECMS Summer Research Scholarship 2017
2017, Christo Pyromallis, Computer Science Student, Undergraduate Project
2017, Ryan Matulick, Computer Science Student, Undergraduate Project
2016-2017, James Kortman, Computer Science Student and Winner of ECMS Summer Research Scholarship 2016
|2017 - ongoing||IEEE Brain||United States|
|2017 - ongoing||ACM SIGEVO||United States|
|2017 - ongoing||IEEE Theoretical Foundations of Bio-inspired Computation Task Force||United Kingdom|
|2017 - ongoing||IEEE Women in Engineering||United States|
|2017 - ongoing||IEEE Computational Intelligence Society||United States|
|2017 - ongoing||IEEE Membership||United States|
|2017 - ongoing||Association for Computing Machinery||United States|
|2016 - ongoing||Australian Network for Art and Technology||Australia|
|2016 - ongoing||ASIA PACIFIC NEURAL NETWORK SOCIETY (APNNS)||Japan|
|2015 - ongoing||University Theatre Guild||Australia|
|2018 - ongoing||Member||IEEE Congress on Evolutionary Computation|
|2016 - ongoing||Member||Australasian Conference on Artificial Life and Computational Intelligence (ACALCI 2017)|