Julian Francis Miller
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Julian Francis Miller has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Andrew James Turner
The University of York
3 shared publications - Domagoj Jakobovic
University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, Croatia
3 shared publications - Stjepan Picek
Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
3 shared publications - Claude Carlet
University of Paris 8 Saint-Denis France
2 shared publications - Alberto Moraglio
University of Exeter
1 shared publication - Ana Lucia Cetertich Bazzan
UFRGS
1 shared publication
Latest Publications
- 3 November 2021
- Published by MIT Press in Artificial Life
- Vol. 27 (3-4) , 1-36
IMPROBED: Multiple Problem-Solving Brain via Evolved Developmental Programs
Artificial neural networks (ANNs) were originally inspired by the brain; however, very few models use evolution and development, both of which are fundamental to the construction of the brain. We describe a simple neural model, called IMPROBED, in which two neural programs construct an artificial brain that can simultaneously solve multiple computational problems. One program represents the neuron soma and the other the dendrite. The soma program decides whether neurons move, change, die, or replicate. The dendrite program decides whether dendrites extend, change, die, or replicate. Since developmental programs build networks that change over time, it is necessary to define new problem classes that are suitable to evaluate such approaches. We show that the pair of evolved programs can build a single network from which multiple conventional ANNs can be extracted, each of which can solve a different computational problem. Our approach is quite general and it could be applied to a much wider variety of problems.
- 3 November 2021
- Published by MIT Press in Artificial Life
- Vol. 27 (3-4) , 1-36
IMPROBED: Multiple Problem-Solving Brain via Evolved Developmental Programs
Artificial neural networks (ANNs) were originally inspired by the brain; however, very few models use evolution and development, both of which are fundamental to the construction of the brain. We describe a simple neural model, called IMPROBED, in which two neural programs construct an artificial brain that can simultaneously solve multiple computational problems. One program represents the neuron soma and the other the dendrite. The soma program decides whether neurons move, change, die, or replicate. The dendrite program decides whether dendrites extend, change, die, or replicate. Since developmental programs build networks that change over time, it is necessary to define new problem classes that are suitable to evaluate such approaches. We show that the pair of evolved programs can build a single network from which multiple conventional ANNs can be extracted, each of which can solve a different computational problem. Our approach is quite general and it could be applied to a much wider variety of problems.
- Open Access
- 1 January 2020
- Published by MIT Press
- p. 473-482
Evolving developmental neural networks to solve multiple problems
We describe a neural model in which two evolved neural programs undergo development and form neural networks. The programs decide whether neurons and their dendrites move, change, die or replicate. We show that the programs can build a neural structure from which multiple conventional ANNs can be extracted each of which can solve a different computational problem. We describe a neural model in which two evolved neural programs undergo development and form neural networks. The programs decide whether neurons and their dendrites move, change, die or replicate. We show that the programs can build a neural structure from which multiple conventional ANNs can be extracted each of which can solve a different computational problem. We describe a neural model in which two evolved neural programs undergo development and form neural networks. The programs decide whether neurons and their dendrites move, change, die or replicate. We show that the programs can build a neural structure from which multiple conventional ANNs can be extracted each of which can solve a different computational problem.
- 1 January 2020
- Published by MIT Press
- p. 473-482
Open AccessEvolving developmental neural networks to solve multiple problems
We describe a neural model in which two evolved neural programs undergo development and form neural networks. The programs decide whether neurons and their dendrites move, change, die or replicate. We show that the programs can build a neural structure from which multiple conventional ANNs can be extracted each of which can solve a different computational problem. We describe a neural model in which two evolved neural programs undergo development and form neural networks. The programs decide whether neurons and their dendrites move, change, die or replicate. We show that the programs can build a neural structure from which multiple conventional ANNs can be extracted each of which can solve a different computational problem. We describe a neural model in which two evolved neural programs undergo development and form neural networks. The programs decide whether neurons and their dendrites move, change, die or replicate. We show that the programs can build a neural structure from which multiple conventional ANNs can be extracted each of which can solve a different computational problem.
- Top Cited PapersOpen Access
- 6 August 2019
- Published by Springer Nature in Genetic Programming and Evolvable Machines
- Vol. 21 (1-2) , 129-168
Cartesian genetic programming: its status and future
- 6 August 2019
- Published by Springer Nature in Genetic Programming and Evolvable Machines
- Vol. 21 (1-2) , 129-168
Top Cited PapersOpen AccessCartesian genetic programming: its status and future
- Open Access
- 24 April 2019
- Published by Springer Nature in Natural Computing
- Vol. 18 (3) , 515-526
The alchemy of computation: designing with the unknown
- 24 April 2019
- Published by Springer Nature in Natural Computing
- Vol. 18 (3) , 515-526
Open AccessThe alchemy of computation: designing with the unknown
- 17 April 2019
- Published by Springer Nature
- p. 23-71
Evolving Programs to Build Artificial Neural Networks
- 17 April 2019
- Published by Springer Nature
- p. 23-71
Evolving Programs to Build Artificial Neural Networks
- 21 August 2018
- Published by Springer Nature
- p. 477-489
Tutorials at PPSN 2018
- 1 December 2016
- Published by MIT Press in Evolutionary Computation
- Vol. 24 (4) , 667-694
Evolutionary Algorithms for Boolean Functions in Diverse Domains of Cryptography
The role of Boolean functions is prominent in several areas including cryptography, sequences, and coding theory. Therefore, various methods for the construction of Boolean functions with desired properties are of direct interest. New motivations on the role of Boolean functions in cryptography with attendant new properties have emerged over the years. There are still many combinations of design criteria left unexplored and in this matter evolutionary computation can play a distinct role. This article concentrates on two scenarios for the use of Boolean functions in cryptography. The first uses Boolean functions as the source of the nonlinearity in filter and combiner generators. Although relatively well explored using evolutionary algorithms, it still presents an interesting goal in terms of the practical sizes of Boolean functions. The second scenario appeared rather recently where the objective is to find Boolean functions that have various orders of the correlation immunity and minimal Hamming weight. In both these scenarios we see that evolutionary algorithms are able to find high-quality solutions where genetic programming performs the best.
- 1 December 2016
- Published by MIT Press in Evolutionary Computation
- Vol. 24 (4) , 667-694
Evolutionary Algorithms for Boolean Functions in Diverse Domains of Cryptography
The role of Boolean functions is prominent in several areas including cryptography, sequences, and coding theory. Therefore, various methods for the construction of Boolean functions with desired properties are of direct interest. New motivations on the role of Boolean functions in cryptography with attendant new properties have emerged over the years. There are still many combinations of design criteria left unexplored and in this matter evolutionary computation can play a distinct role. This article concentrates on two scenarios for the use of Boolean functions in cryptography. The first uses Boolean functions as the source of the nonlinearity in filter and combiner generators. Although relatively well explored using evolutionary algorithms, it still presents an interesting goal in terms of the practical sizes of Boolean functions. The second scenario appeared rather recently where the objective is to find Boolean functions that have various orders of the correlation immunity and minimal Hamming weight. In both these scenarios we see that evolutionary algorithms are able to find high-quality solutions where genetic programming performs the best.
- 24 March 2016
- Published by Springer Nature
- p. 294-310
Iterative Cartesian Genetic Programming: Creating General Algorithms for Solving Travelling Salesman Problems
- 24 March 2016
- Published by Springer Nature
- p. 294-310
Iterative Cartesian Genetic Programming: Creating General Algorithms for Solving Travelling Salesman Problems