scispace - formally typeset
Search or ask a question
Author

Andy Lomas

Other affiliations: Framestore
Bio: Andy Lomas is an academic researcher from Goldsmiths, University of London. The author has contributed to research in topics: Evolutionary art & Generative systems. The author has an hindex of 6, co-authored 19 publications receiving 94 citations. Previous affiliations of Andy Lomas include Framestore.

Papers
More filters
Proceedings ArticleDOI
27 Jul 2014
TL;DR: The aim is to create structures emergently: exploring generic similarities between many different forms in nature rather than recreating any particular organism, revealing universal archetypal forms that can come from growth-like processes rather than top-down externally engineered design.
Abstract: Cellular Forms: a series of computationally created artworks that uses digital simulation of morphogenetic processes. The aim is to create structures emergently: exploring generic similarities between many different forms in nature rather than recreating any particular organism, revealing universal archetypal forms that can come from growth-like processes rather than top-down externally engineered design.

24 citations

Journal ArticleDOI
TL;DR: In this article, the authors investigate the relationship between image measures, such as complexity, and human aesthetic evaluation, and use dimension reduction methods to visualise both genotype and phenotype space in order to support the exploration of new territory in a generative system.
Abstract: Accurate evaluation of human aesthetic preferences represents a major challenge for creative evolutionary and generative systems research. Prior work has tended to focus on feature measures of the artefact, such as symmetry, complexity and coherence. However, research models from psychology suggest that human aesthetic experiences encapsulate factors beyond the artefact, making accurate computational models very difficult to design. The interactive genetic algorithm circumvents the problem through human-in-the-loop, subjective evaluation of aesthetics, but is limited due to user fatigue and small population sizes. In this paper, we look at how recent advances in deep learning can assist in automating personal aesthetic judgement. Using a leading artist’s computer art dataset, we investigate the relationship between image measures, such as complexity, and human aesthetic evaluation. We use dimension reduction methods to visualise both genotype and phenotype space in order to support the exploration of new territory in a generative system. Convolutional neural networks trained on the artist’s prior aesthetic evaluations are used to suggest new possibilities similar or between known high-quality genotype-phenotype mappings. We integrate this classification and discovery system into a software tool for evolving complex generative art and design.

19 citations

Proceedings ArticleDOI
12 Jul 2016
TL;DR: Species Explorer is described, an interface to allow creative exploration of generative systems with multi-dimensional parameter spaces that combines both evolutionary and machine learning approaches.
Abstract: This paper describes Species Explorer, an interface to allow creative exploration of generative systems with multi-dimensional parameter spaces. The system combines both evolutionary and machine learning approaches. It was originally designed to assist creating work for the author's 'Cellular Forms' and 'Hybrid Forms' series, where a large number of parameters are used to yield emergent results, but is a general framework that could be applied to many other systems.

18 citations

Journal ArticleDOI
TL;DR: This article argues for a collaborative relationship with the computer that can free the artist to more fearlessly engage with the challenges of working with emergent systems that exhibit complex unpredictable behavior.
Abstract: This article reviews the development of the author’s computational art practice, where the computer is used both as a device that provides the medium for generation of art (‘computer as art’) as well as acting actively as an assistant in the process of creating art (‘computer as artist’s assistant’), helping explore the space of possibilities afforded by generative systems Drawing analogies with Kasparov’s Advanced Chess and the deliberate development of unstable aircraft using fly-by-wire technology, the article argues for a collaborative relationship with the computer that can free the artist to more fearlessly engage with the challenges of working with emergent systems that exhibit complex unpredictable behavior The article also describes ‘Species Explorer’, the system the author has created in response to these challenges to assist exploration of the possibilities afforded by parametrically driven generative systems This system provides a framework to allow the user to use a number of different techniques to explore new parameter combinations, including genetic algorithms, and machine learning methods As the system learns the artist’s preferences the relationship with the computer can be considered to change from one of assistance to collaboration

13 citations

Book ChapterDOI
15 Apr 2020
TL;DR: In this paper, the authors use a leading artist's computer art dataset to visualise both genotype and phenotype space in order to support the exploration of new territory in any generative system.
Abstract: A bottleneck in any evolutionary art system is aesthetic evaluation. Many different methods have been proposed to automate the evaluation of aesthetics, including measures of symmetry, coherence, complexity, contrast and grouping. The interactive genetic algorithm (IGA) relies on human-in-the-loop, subjective evaluation of aesthetics, but limits possibilities for large search due to user fatigue and small population sizes. In this paper we look at how recent advances in deep learning can assist in automating personal aesthetic judgement. Using a leading artist’s computer art dataset, we use dimensionality reduction methods to visualise both genotype and phenotype space in order to support the exploration of new territory in any generative system. Convolutional Neural Networks trained on the user’s prior aesthetic evaluations are used to suggest new possibilities similar or between known high quality genotype-phenotype mappings.

13 citations


Cited by
More filters
01 Jan 2016
TL;DR: Thank you very much for downloading the blind watchmaker why the evidence of evolution reveals a universe without design, but end up in malicious downloads.
Abstract: Thank you very much for downloading the blind watchmaker why the evidence of evolution reveals a universe without design. Maybe you have knowledge that, people have look hundreds times for their favorite books like this the blind watchmaker why the evidence of evolution reveals a universe without design, but end up in malicious downloads. Rather than enjoying a good book with a cup of tea in the afternoon, instead they juggled with some harmful bugs inside their desktop computer.

161 citations

Journal ArticleDOI
20 Jun 2016
TL;DR: Mushtari as mentioned in this paper is a multimaterial 3D printed fluidic wearable designed to culture microbial communities, which is a computational design environment for additive manufacturing of geometrically complex and materially heterogeneous fluidic channels.
Abstract: Despite significant advances in synthetic biology at industrial scales, digital fabrication challenges have, to date, precluded its implementation at the product scale. We present, Mushtari, a multimaterial 3D printed fluidic wearable designed to culture microbial communities. Thereby we introduce a computational design environment for additive manufacturing of geometrically complex and materially heterogeneous fluidic channels. We demonstrate how controlled variation of geometrical and optical properties at high spatial resolution can be achieved through a combination of computational growth modeling and multimaterial bitmap printing. Furthermore, we present the implementation, characterization, and evaluation of support methods for creating product-scale fluidics. Finally, we explore the cytotoxicity of 3D printed materials in culture studies with the model microorganisms, Escherichia coli and Bacillus subtilis. The results point toward design possibilities that lie at the intersection of compu...

33 citations

Journal ArticleDOI
01 Jun 2004

27 citations

Book ChapterDOI
01 Jan 2020
TL;DR: An ML model of non-trivial Proxies of Human Interpretability can be learned from human feedback, then this model can be incorporated within an ML training process to directly optimize for interpretability, and the results show that the use of this model leads to formulas that are significantly more or equally accurate.
Abstract: Many risk-sensitive applications require Machine Learning (ML) models to be interpretable. Attempts to obtain interpretable models typically rely on tuning, by trial-and-error, hyper-parameters of model complexity that are only loosely related to interpretability. We show that it is instead possible to take a meta-learning approach: an ML model of non-trivial Proxies of Human Interpretability (PHIs) can be learned from human feedback, then this model can be incorporated within an ML training process to directly optimize for interpretability. We show this for evolutionary symbolic regression. We first design and distribute a survey finalized at finding a link between features of mathematical formulas and two established PHIs, simulatability and decomposability. Next, we use the resulting dataset to learn an ML model of interpretability. Lastly, we query this model to estimate the interpretability of evolving solutions within bi-objective genetic programming. We perform experiments on five synthetic and eight real-world symbolic regression problems, comparing to the traditional use of solution size minimization. The results show that the use of our model leads to formulas that are, for a same level of accuracy-interpretability trade-off, either significantly more or equally accurate. Moreover, the formulas are also arguably more interpretable. Given the very positive results, we believe that our approach represents an important stepping stone for the design of next-generation interpretable (evolutionary) ML algorithms.

26 citations

Proceedings ArticleDOI
27 Jul 2014
TL;DR: The aim is to create structures emergently: exploring generic similarities between many different forms in nature rather than recreating any particular organism, revealing universal archetypal forms that can come from growth-like processes rather than top-down externally engineered design.
Abstract: Cellular Forms: a series of computationally created artworks that uses digital simulation of morphogenetic processes. The aim is to create structures emergently: exploring generic similarities between many different forms in nature rather than recreating any particular organism, revealing universal archetypal forms that can come from growth-like processes rather than top-down externally engineered design.

24 citations